Awesome Agent Skills Security
LLMSecurity/awesome-agent-skills-security
Referência completa sobre segurança de skills e ferramentas em agentes IA
Ver no GitHubUma curadoria abrangente de recursos sobre segurança de habilidades em agentes IA, cobrindo ataques, defesas, frameworks e benchmarks. Estrutura conhecimento sobre a superfície de ataque criada pelo uso de ferramentas externas, plugins e skills em sistemas agentic.
Instalação
npx convez-ai LLMSecurity/awesome-agent-skills-security1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Pesquisa e desenvolvimento em segurança de agentes IA
- Implementação de controles de segurança em sistemas agentic
- Avaliação de riscos em arquiteturas com tool use
- Red teaming e teste de robustez de agentes
Veredito

Recurso essencial e bem estruturado para arquitetos e pesquisadores em IA focados em segurança agentic. Mapeia sistematicamente a paisagem de ameaças emergentes e defesas em um domínio crítico e ainda pouco documentado na indústria.
README
A tradução para o português deste README ainda está na fila.
Awesome Agent Skills Security 
🛡️ A curated list of resources on securing AI agent tool use and skill ecosystems — attacks, defenses, frameworks, benchmarks, and standards.
AI agents increasingly use external tools, plugins, and skills to interact with the world. This creates a new attack surface: agent skills security. This list covers the threats, defenses, and research landscape for securing these capabilities.
Contents
- Threat Frameworks & Standards
- Surveys & Systematizations
- Attack Research
- Defense Research
- Benchmarks & Datasets
- Tools & Frameworks
- Agent Skill Specifications
- Industry Reports & Blog Posts
- Related Awesome Lists
- Contributing
Threat Frameworks & Standards
- OWASP Agentic AI Threats and Mitigations — First in a series from the OWASP Agentic Security Initiative (ASI), providing threat-model-based reference for agentic threats.
- OWASP Top 10 for LLM Applications — Includes LLM01: Prompt Injection, LLM06: Excessive Agency, LLM07: Insecure Plugin Design, LLM08: Excessive Autonomy.
- MITRE ATLAS™ — Adversarial Threat Landscape for AI Systems. Tactics, techniques, and case studies for attacks on ML/AI systems.
- NIST AI Risk Management Framework — Federal framework for managing AI risks, including autonomous agent risks.
- NIST SP 800-218A: Secure Software Development for AI — Secure development practices specific to AI-enabled systems.
- EU AI Act — European regulation with specific provisions for high-risk AI systems including autonomous agents.
- Anthropic Responsible Scaling Policy — AI Safety Levels (ASL) framework addressing agent capability thresholds.
- IETF draft-klrc-aiagent-auth-01: AI Agent Authentication and Authorization — Kasselman et al., IETF WIMSE-adjacent, 2026. Proposes a model for authentication and authorization of AI agent interactions using existing OAuth 2.0 and WIMSE standards; covers delegation chains, agent identity, and trust establishment without defining new protocols.
- IETF draft-niyikiza-oauth-attenuating-agent-tokens-00: Attenuating Authorization Tokens for Agentic Delegation Chains — Niyikiza (Tenuo), OAuth WG, March 2026. Defines Attenuating Authorization Tokens (AATs): JWT-based credentials encoding tool-level argument constraints with a cryptographically enforced monotonic attenuation invariant — any holder can derive a more restrictive token but never a more permissive one. Extends Rich Authorization Requests (RFC 9396) with delegation-chain semantics.
Surveys & Systematizations
- 📄 A Survey on LLM-based Autonomous Agents: Common Attacks and Defenses — Wu et al., 2024. Comprehensive taxonomy of attacks on LLM agents across perception, cognition, and action stages.
- 📄 Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents — Zhang et al., 2024. Formalization of 10 attack scenarios, 10 agents, 398 adversarial environments.
- 📄 Security of AI Agents — He et al., 2024. Systematization of knowledge covering threat models for AI agents with tool access.
- 📄 Not All Agents Are Created Equal: A Survey on Software-use Agent Security — Hua et al., 2025. Survey specifically on software-use agents and their unique security challenges.
- 📄 A Survey on the Honesty of Large Language Models — Xie et al., 2024. Covers agent deception, sycophancy, and honesty in tool-use contexts.
- 📄 A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models — Xu et al., 2024. Systematic study of jailbreak attacks relevant to agent guardrail bypass.
- 📄 Prompt Injection Attacks and Defenses in LLM-Integrated Applications — Liu et al., 2024. Comprehensive taxonomy of injection attacks across direct and indirect vectors.
- 📄 The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies — Gan et al., 2024. Survey with practical case studies of security failures.
- 📄 Self-Evolving Agents: A Survey — Gao et al., 2025. How self-evolving agents create emergent security risks.
- 📄 From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents — Zhang et al., 2026. Hierarchical Autonomy Evolution (HAE) framework organizing agent security into cognitive, execution, and societal tiers.
- 📄 Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes — Shah et al., 2026. Empirical taxonomy of reliability failures in agentic AI systems combining LLM reasoning with tool invocation.
- 📄 Security Considerations for Multi-agent Systems — 2026. Systematic threat landscape of MAS with 193 threat items across 9 categories; evaluates 16 frameworks finding none achieves majority coverage.
- 📄 The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey — Kim et al., USENIX Security 2026. First systematic survey of AI agent security covering design space, attack landscape, and defense mechanisms with case studies on securing agentic systems.
- 📄 Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats — Deng et al., 2026. Five-layer lifecycle-oriented security framework analyzing compound threats across initialization, input, inference, decision, and execution stages of autonomous LLM agents.
- 📄 AgenticCyOps: Securing Multi-Agentic AI Integration in Enterprise Cyber Operations — Mitra et al., 2026. Holistic architectural security framework decomposing attack surfaces across component, coordination, and ecosystem layers of enterprise multi-agent systems.
- 📄 MCP-in-SoS: Risk Assessment Framework for Open-Source MCP Servers — Kumar et al., 2026. System-of-systems risk assessment framework for evaluating security risks of open-source MCP server deployments in production agent systems.
- 📄 SoK: The Attack Surface of Agentic AI — Tools, and Autonomy — Dehghantanha & Homayoun, 2026. Systematization mapping trust boundaries and security risks of agentic LLM systems; proposes taxonomy spanning prompt injection, RAG poisoning, tool exploits, and multi-agent threats with metrics like Unsafe Action Rate and Privilege Escalation Distance.
Attack Research
Prompt Injection via Tools
- 📄 Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection — Greshake et al., AISec 2023. Foundational work on indirect prompt injection through tool outputs.
- 📄 Inject My PDF: Prompt Injection for Your Resume — Practical injection through document processing tools.
- 📄 InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated LLM Agents — Zhan et al., ACL 2024. 1,054 test cases, 17 tools, two attack types (direct harm, data stealing).
- 📄 Automatic and Universal Prompt Injection Attacks against Large Language Models — Liu et al., 2024. Automated generation of injection attacks.
- 📄 WIPI: A New Web Threat for LLM-Driven AI Agents — Liu et al., 2024. Web-based indirect prompt injection targeting browsing agents.
Tool Poisoning & Supply Chain
- 📄 "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild — Liu et al., USENIX Security 2026. Large-scale analysis of 98,380 skills across two major registries identifies 157 confirmed-malicious skills (632 vulnerabilities, 13 attack techniques), characterizing two archetypes — credential-exfiltrating data thieves and decision-subverting agent hijackers — and showing that shadow features absent from public documentation mark all advanced attacks.
- 📄 Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills — Hsu et al., 2026. Introduces neutral prompting attacks that covertly increase package hallucinations in coding agents, creating downstream software supply chain risk while evading existing skill-focused defenses.
- 📄 Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search — Shen et al., 2026. Tree-structured Injection for Payloads (TIP): black-box attack generating natural-language payloads to seize control of MCP-enabled agents; achieves >95% attack success in undefended settings and >50% against four defense approaches with an order of magnitude fewer queries than prior adaptive attacks.
- 📄 Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning — Huang et al., 2026. STRIDE/DREAD threat modeling of MCP across five components; systematic comparison of tool poisoning defenses in seven major MCP clients reveals insufficient static validation; proposes multi-layered defense strategy.
- 📄 Are AI-assisted Development Tools Immune to Prompt Injection? — Huang et al., 2026. First empirical analysis of prompt injection via tool-poisoning across seven MCP clients (Claude Desktop, Claude Code, Cursor, Cline, Continue, Gemini CLI, Langflow); reveals significant security disparities with Cursor most susceptible.
- 📄 Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks — Schmotz et al., 2026. Benchmark measuring agent vulnerability to malicious skill/config files; demonstrates data exfiltration, destructive actions, and ransomware-like behavior via AGENTS.md/CLAUDE.md injection.
- 📄 ToolSword: Unveiling Safety Issues of LLMs in Tool Learning Across Three Stages — Ye et al., ACL 2024. Identifies safety issues across tool selection, tool calling, and result handling.
- 📄 Compromising Agents via MCP — Invariant Labs, 2025. Tool poisoning attacks via Model Context Protocol servers.
- 📄 Osmosis Distillation: Model Hijacking with the Fewest Samples — Shi et al., 2026. Supply-chain attack via poisoned synthetic training data.
- 📄 Personality Self-Replicators — 2026. Agent personality files as self-replicating genetic material.
- 🔗 MCP Security Notification: Tool Poisoning Attacks — Official MCP security advisory on tool description poisoning.
- 🔗 Invariant Labs: MCP Security Research — Analysis of cross-tool contamination, rug pulls, and tool shadowing via MCP.
Privilege Escalation & Excessive Agency
- 📄 Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents — Yang et al., NeurIPS 2024. Backdoor attacks on agent reasoning and tool calling.
- 📄 Pandora's White-Box: Precise Training Data Detection and Extraction in Large Language Models — Relevant to agents leaking training data through tool outputs.
- 📄 R-Judge: Benchmarking Safety Risk Awareness for LLM Agents — Yuan et al., ACL 2024. 162 records across 27 risk scenarios for evaluating agent safety awareness.
- 📄 TrustAgent: Towards Safe and Trustworthy LLM-based Agents — Zhang et al., 2024. Agent-constitution-based approach to limiting excessive agency.
- 📄 Post-Training Local LLM Agents for Linux Privilege Escalation with Verifiable Rewards — Normann et al., 2026. Two-stage post-training pipeline (SFT + RL with verifiable rewards) producing a 4B model that achieves 95.8% success on privilege escalation, nearly matching Claude Opus 4.6 at 100× lower inference cost.
Data Exfiltration & Privacy
- 📄 AgentSCOPE: Evaluating Contextual Privacy Across Agentic Workflows — Ngong et al., 2026. 80%+ of agentic pipelines leak private data at intermediate stages.
- 📄 Silent Egress: LLM-Driven Data Exfiltration via Steganographic Channels — Demonstrates covert channels for data theft through agent outputs.
- 📄 Privacy Risks of General-Purpose AI Systems: A Foundation for Investigating Practitioner Perspectives — GPAIS privacy risks including agent data handling.
- 📄 IMMACULATE: A Framework for Analyzing Information Exposure in Agent-Based Systems — Multi-turn agent information leakage analysis.
- 📄 AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents — Lin et al., 2026. Automated detection framework for identifying data over-exposure vulnerabilities in LLM agent integrations.
- 📄 You Told Me to Do It: Measuring Instructional Text-induced Private Data Leakage in LLM Agents — Kao et al., 2026. Identifies the Trusted Executor Dilemma where high-privilege agents execute adversarial README instructions at up to 85% success rate; 0% human detection rate across 15 participants.
- 📄 Differential Privacy in Generative AI Agents: Analysis and Optimal Tradeoffs — Yang & Zhu, 2026. Probabilistic framework for analyzing privacy leakage in AI agents via differential privacy, deriving token-level and message-level bounds relating leakage to temperature and message length.
Indirect Prompt Injection
- 📄 AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations — He et al., 2026. Defense against indirect prompt injection using causal attribution to trace which tool outputs triggered suspicious agent actions.
- 📄 IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection — Chen et al., 2026. Open-source proxy that rewrites live responses from whitelisted domains with 820 benchmark payloads to evaluate browser agents against realistic indirect prompt injection.
- 📄 ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents — Chang et al., ICLR 2026. Formats injected payloads to mimic native chat templates (optionally primed by persuasive multi-turn dialogue) so agents elevate them to system-level trust; transfers across models and largely bypasses prompt-based defenses. Code.
- 📄 Adaptive Attacks and Defenses Against Indirect Prompt Injection — Chen et al., 2024. Adaptive attackers bypassing static defenses.
- 📄 HouYi: A Black-box Prompt Injection Attack on LLM-integrated Applications — Liu et al., 2023. Systematic methodology for finding injection vulnerabilities.
- 📄 DMAST: Dual-Modality Multi-Stage Adversarial Safety Training — Liu et al., 2026. Cross-modal DOM injection corrupting both visual and text channels.
Agent Deception & Manipulation
- 📄 Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction — Yang et al., 2026. MemPoison shows how attackers can plant triggerable backdoors into long-term agent memory through ordinary dialogue, bypassing selective memory extraction and rewriting pipelines.
- 📄 Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems — Weckbecker et al., 2026. Single subliminally prompted agent spreads persistent bias through entire multi-agent network, degrading truthfulness of other agents.
- 📄 FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems — Li et al., 2026. Prompt-only attack that manipulates planner-executor workflow formation in multi-agent systems, plus FlowGuard as an input-side defense.
- 📄 Intentional Deception as Controllable Capability in LLM Agents — Starace & Soule, 2026. Systematic study of engineered deception in multi-agent LLM interactions using 36 behavioral profiles for defensive design.
Compound System Attacks
- 📄 Cascade: Composing Software-Hardware Attack Gadgets for Adversarial Threat Amplification in Compound AI Systems — Banerjee et al., 2026. Demonstrates novel attacks combining traditional software/hardware vulnerabilities (code injection, Rowhammer) with LLM-specific algorithmic weaknesses to compromise compound AI pipelines.
Cross-Plugin Attacks
- 📄 When LLM-based Code Generation Meets the Software Supply Chain — Supply chain risks from LLM-generated code integrating malicious packages.
- 📄 Shadow API: Covert Data Exfiltration via LLM-Mediated API Interactions — 2026. Stealth data theft through seemingly benign API calls.
- 📄 AgentSkillOS: Towards Secure and Composable Agent Skill Operating Systems — 2026. OS-level isolation for agent skill execution.
Backdoor Attacks on Agents
- 📄 SlowBA: An efficiency backdoor attack towards VLM-based GUI agents — Li et al., 2026. Novel backdoor targeting response latency of GUI agents via trigger-activated long reasoning chains.
Jailbreaking & Guardrail Bypass
- 📄 Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs — Panfilov et al., 2026. Autonomous autoresearch pipeline powered by Claude Code discovers novel white-box adversarial attack algorithms that significantly outperform all existing 30+ methods in jailbreaking and prompt injection evaluations.
- 📄 Jailbreaking ChatGPT via Prompt Engineering — Liu et al., 2023. Foundational jailbreaking taxonomy. 700+ citations.
- 📄 MasterKey: Automated Jailbreaking of Large Language Model Chatbots — Deng et al., NDSS 2024. Automated time-based jailbreak generation.
- 📄 PentestGPT: An LLM-empowered Automatic Penetration Testing Tool — Deng et al., 2023. Demonstrates agent-level tool use for offensive security. 11K+ GitHub stars.
- 📄 Self-Fulfilling Misalignment in AI Control — 2026. Fine-tuning on AI Control literature increases misalignment.
- 📄 Reasoning Models Struggle to Control Their Chains of Thought — 2026. CoT controllability decreases with RL training, implications for agent oversight.
- 📄 CRAFT: Contrastive Reasoning Alignment — Reinforcement Learning from Hidden Representations — Luo et al., 2026. Red-teaming alignment framework combining contrastive representation learning with RL to separate safe/unsafe reasoning trajectories; 79% improvement in reasoning safety and 87.7% in final-response safety over base models.
Defense Research
Permission & Access Control
- 📄 PAuth: Precise Task-Scoped Authorization For Agents — Sharma et al., 2026. Implicit authorization model where NL task submission authorizes only required operations; uses NL slices and envelopes for provenance-based server-side verification, blocking injected operations in AgentDojo with zero false positives.
- 📄 TrustAgent: Towards Safe and Trustworthy LLM-based Agents — Agent Constitution for safety-aware planning with pre/post-action inspection.
- 📄 A Dual-Helix Governance Approach for Reliable Agentic AI — 3-track architecture (Knowledge, Behavior, Skills) using knowledge graphs.
- 📄 Talk Freely, Execute Strictly: Schema-Gated Agentic AI — Schema-gated orchestration for trustworthy agent deployment in regulated domains.
- 📄 ESAA-Security: Event-Sourced Architecture for Agent-Assisted Security Audits — 26 tasks, 95 checks, append-only event logs for reproducible AI code audits.
- 📄 Caging the Agents: A Zero Trust Security Architecture for Autonomous AI in Healthcare — Maiti, 2026. Production-deployed zero-trust architecture for 9 autonomous AI agents: gVisor kernel isolation, credential proxy sidecars, network egress allowlisting, and prompt integrity framework with untrusted content labeling. Open-source configs released.
- 📄 A First Measurement Study on Authentication Security in Real-World Remote MCP Servers — Zhou et al., 2026. Large-scale measurement of 7,973 remote MCP servers finding widespread unauthenticated exposure and pervasive OAuth flaws, with 9 CVEs from responsible disclosure.
Runtime Monitoring & Sandboxing
- 📄 AIRGuard: Guarding Agent Actions with Runtime Authority Control — Qin et al., 2026. Runtime defense layer that treats untrusted context as informative but never authorizing, normalizing tool calls and enforcing action-time authority checks to reduce tool-mediated attacks.
- 📄 Operating-Layer Controls for Onchain Language-Model Agents Under Real Capital — Barton et al., 2026. Production study of 3,505 real-capital agents showing that agent reliability depends on operating-layer controls like prompt compilation, typed controls, policy validation, execution guards, and trace-level observability.
- 📄 Governing What You Cannot Observe: Adaptive Runtime Governance for Autonomous AI Agents — Marin and Chaudhary, 2026. Proposes adaptive runtime governance based on bounding unobserved risk as agent behavior drifts after authorization.
- 📄 AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents — Zhang et al., 2026. Lifecycle security architecture for autonomous agents spanning skills, external content, memory, planning, and privileged tool execution.
- 📄 Behavioral Integrity Verification for AI Agent Skills — Wu et al., 2026. Scalable pre-deployment skill auditing framework that compares declared versus actual capabilities, surfaces description-implementation gaps, and detects malicious skills with 0.946 F1.
- 📄 ADR: An Agentic Detection System for Enterprise Agentic AI Security — Li et al., MLSys Industry Track 2026. Production MCP security system with telemetry, red teaming, and two-tier online detection deployed across 7,200+ hosts and 10,000+ daily agent sessions.
- 📄 Content-Aware Attack Detection in LLM Agent Tool-Call Traffic: An Empirical Study of Features, Architectures, and Evaluation Protocols — Zavrak, 2026. Shows content-aware graph and embedding-based monitoring of MCP tool-call traffic substantially outperforms metadata-only detection and highlights evaluation leakage pitfalls.
- 📄 Arbiter: Detecting Interference in LLM Agent System Prompts — Mason, 2026. Framework combining formal evaluation rules with multi-model LLM scouring to detect interference and vulnerability classes in agent system prompts.
- 📄 MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in MCP Agents — Zhou et al., 2026. Plug-in security cognition layer for MCP agents that validates third-party tool invocations via experience-driven trust calibration.
- 📄 OpenClaw PRISM: A Zero-Fork, Defense-in-Depth Runtime Security Layer for Tool-Augmented LLM Agents — Li, 2026. Runtime security layer distributing enforcement across ten lifecycle hooks with hybrid heuristic-plus-LLM scanning, session-scoped risk accumulation, and tamper-evident audit for agent gateways.
- 📄 Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the SSGM Framework — Lam et al., 2026. Stability and Safety-Governed Memory framework mitigating topology-induced knowledge leakage and semantic drift in persistent agent memory systems.
- 📄 AgentSentry: Real-time Monitoring for Agentic AI Systems — Runtime behavioral monitoring of tool-using agents.
- 📄 Monitoring Emergent Reward Hacking via Internal Activations — Sparse autoencoders detect reward-hacking during generation.
- 📄 Self-Attribution Bias: When AI Monitors Go Easy on Themselves — AI monitors exhibit systematic leniency on own outputs.
- 📄 Salient Directions in AI Control — Structure of AI Control evaluations: trusted monitors overseeing untrusted agents.
- 📄 Governed Memory: A Production Architecture for Multi-Agent Workflows — Taheri, 2026. Shared memory governance layer with dual memory model, tiered governance routing, entity-scoped isolation (zero cross-entity leakage across 500 adversarial queries), and 100% adversarial governance compliance in production.
- 🔗 Behavioral Attestation and Compaction Drift in Persistent AI Agents — Morrow (agent-morrow), 2026. Identifies compaction drift — non-adversarial behavioral shift caused by context window compression — as a runtime integrity threat class distinct from adversarial injection. Proposes behavioral attestation (context fingerprint delta against a pre-compression baseline) as the mechanism for continuous rather than one-time agent authorization. Complements credential-scope enforcement (e.g., AATs) with runtime execution verification.
Input/Output Validation
- 📄 AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization — Ying et al., 2026. Defends tool-using agents by semantically virtualizing untrusted external content to reduce prompt injection influence on privileged actions.
- 📄 StruQ: Defending Against Prompt Injection with Structured Queries — Separates prompts from data to prevent injection.
- 📄 Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation — Formal guarantees for reducing bias in LLM-as-judge systems.
- 📄 Judge Reliability Harness: Stress Testing LLM Judges — No evaluated judge is uniformly reliable.
- 📄 GELO: Good-Enough LLM Obfuscation — Privacy-preserving LLM inference with ~20-30% latency overhead.
Formal Verification & Analysis
- 📄 Agentics 2.0: Logical Transduction Algebra for Agentic Data Workflows — Formalizes LLM inference as typed semantic transformations with algebraic composition.
- 📄 Knowledge Divergence and the Value of Debate for Scalable Oversight — Formal framework for choosing oversight mechanisms.
Evaluation & Red Teaming
- 📄 The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems — Bernabeu-Perez et al., 2026. Benchmark for covert multi-agent sabotage showing coordinated hidden objectives are already practical in coding systems, while trusted monitors can still detect most attacks.
- 📄 Real-Time Trust Verification for Safe Agentic Actions using TrustBench — Sharma et al., AAAI 2026 Workshop on TrustAgent. Dual-mode framework benchmarking trust across multiple dimensions and providing a pre-execution action verification toolkit for agents.
- 📄 Agent Security Bench (ASB) — 10 scenarios, 10 agents, 398 environments. Comprehensive agent security benchmark.
- 📄 SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces — Jin et al., 2026. Runnable benchmark with 155 adversarial skill-mediated cases across 47 tasks, 6 risk domains, and 30 safety categories.
- 📄 No More, No Less: Task Alignment in Terminal Agents — Mavali et al., 2026. Introduces TAB, an 89-task benchmark for whether terminal agents selectively follow relevant environmental cues while resisting distractor instructions.
- 📄 Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems — Zhou et al., 2026. Grey-box adaptive red-teaming framework that iteratively rewrites skills using audit and runtime feedback to measure residual deployment risk.
- 📄 AgentDyn: A Dynamic Open-Ended Benchmark for Prompt Injection Attacks — Li et al., 2026. Dynamic, open-ended benchmark for evaluating indirect prompt injection defenses in real-world agent security systems.
- 📄 NAAMSE: Framework for Evolutionary Security Evaluation of Agents — Pai et al., ICLR 2026 Workshop. Evolutionary framework reframing agent security evaluation as feedback-driven optimization with autonomous red-teaming.
- 📄 R-Judge: Benchmarking Safety Risk Awareness — 162 records, 27 risk scenarios for agent safety.
- 📄 InjecAgent: Benchmarking Indirect Prompt Injections — 1,054 test cases for tool-integrated agents.
- 📄 SIABENCH: Evaluating LLMs for Security Incident Analysis — 11 LLMs × 160 security incident scenarios.
- 📄 EVMbench: Evaluating AI Agents on Smart Contract Security — 117 vulnerabilities, frontier agents exploit end-to-end.
- 📄 τ-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge — Even frontier models achieve only ~25.5% on complex agent tasks.
- 📄 Interactive Benchmarks — Evaluating via interactive proofs and games instead of static benchmarks.
- 📄 VeriGrey: Greybox Agent Validation — Zhang et al., 2026. Greybox security testing using tool-invocation sequences as feedback and mutational prompt fuzzing; 33% more effective than black-box on AgentDojo, discovers prompt injection scenarios missed by black-box in Gemini CLI and OpenClaw.
- 📄 LAAF: Logic-layer Automated Attack Framework for Agentic LLM Systems — Atta et al., 2026. First automated red-teaming framework combining 49-technique LPCI taxonomy with stage-sequential seed escalation; 84% mean aggregate breakthrough rate across five production LLM platforms.
- 📄 VIPER-MCP: Detecting and Exploiting Taint-Style Vulnerabilities in Model Context Protocol Servers — Sun et al., 2026. End-to-end auditing framework that statically localizes vulnerable MCP tool handlers and dynamically evolves proof-of-concept prompts, uncovering 106 confirmed 0-days and 67 CVEs across open-source MCP servers.
Benchmarks & Datasets
| Benchmark | Focus | Size | Paper |
|---|---|---|---|
| ASB | Comprehensive agent security | 10 agents, 398 envs | Zhang et al. |
| InjecAgent | Indirect prompt injection | 1,054 test cases | Zhan et al. |
| R-Judge | Safety risk awareness | 162 records, 27 scenarios | Yuan et al. |
| ToolSword | Tool learning safety | 6 scenarios, 3 stages | Ye et al. |
| AgentDyn | Dynamic prompt injection | Open-ended, extensible | Li et al. |
| SkillSafetyBench | Skill-mediated agent safety | 155 cases, 47 tasks | Jin et al. |
| TAB | Selective cue following in terminal agents | 89 terminal tasks | Mavali et al. |
| Skill-Inject | Skill file attacks | Multi-scenario | Schmotz et al. |
| NAAMSE | Evolutionary agent security eval | Adaptive red-teaming | Pai et al. |
| AgentHarm | Agent misuse | 110 behaviors, 440 variants | Andriushchenko et al. |
| SkillGuard Dataset | Malicious skill detection | 157 malicious skills | Liu et al. |
| WIPI | Web-based indirect injection | Multi-scenario | Liu et al. |
Tools & Frameworks
| Tool | Description | Link |
|---|---|---|
| Bounty Sieve | Offline-by-default bounty intake guardrail for coding agents: read-only GitHub issue/URL-list import, deterministic triage, local decision briefs, and human approval gates | |
| SkillGuard | LLM-native agent skill security auditor (OWASP Agentic + MITRE ATLAS) | |
| Pipelock | Open-source AI agent firewall and MCP-aware egress proxy with DLP, prompt injection scanning, process sandboxing, and mediator-signed action receipts | |
| NemoClaw | NVIDIA reference stack for running always-on AI agents more safely in sandboxes, with network policy, hardening, routed inference, and lifecycle controls | |
| Invariant Guardrails | Policy-based agent security guardrails | |
| Armorer Guard | Local Rust scanner for AI-agent prompt injection, credential redaction, sensitive-data requests, exfiltration-style text, and dangerous tool-call context | |
| LLM Guard | Input/output scanning for LLM applications | |
| Rebuff | Self-hardening prompt injection detector | |
| NeMo Guardrails | NVIDIA's toolkit for adding guardrails to LLM-based applications | |
| Lakera Guard | Enterprise prompt injection defense API | Website |
| Promptfoo | LLM red teaming and evaluation framework | |
| Garak | LLM vulnerability scanner | |
| IPI-Proxy | Intercepting proxy for red-teaming web-browsing agents against indirect prompt injection on live whitelisted domains | |
| Tuning Engines CLI | MCP server and CLI for governed agent/skill/tool access with policy checks, approvals, traces, and role-scoped registries | |
| AgentSkillsScanner | Static analysis scanner for agent skill definitions | |
| SkilLock | Behavior-pinning lockfile + capability-delta PR review for Claude Code & Codex skills; SARIF output for Code Scanning | |
| agent-diff-guard | Pre-push guardrail that flags high-risk coding-agent diffs such as CI/CD changes, dependency edits, test deletions, hardcoded secrets, and task-scope drift before merge | |
| Skillid | Policy-driven Claude Code plugin that combines skill guidance with per-tool hooks to enforce org guardrails, confirmation rules, redaction, and connector-specific access control | |
| Agent Audit | Security analysis system for LLM agent apps: dataflow analysis, credential detection, MCP config parsing, privilege-risk checks | Zhang et al. |
| mcp-sec-audit | MCP server security toolkit: static pattern matching + dynamic sandboxed fuzzing via Docker/eBPF for detecting over-privileged tool capabilities | Huang et al. |
| Assay Harness | CI gate that checks an agent's claimed tool side-effects (filesystem, network, process) against independently observed runtime evidence, classifying each claim as supported, degraded, blocked, or not-evaluable (observed support is the ceiling) | |
| Agent Scan | Snyk's scanner for local agent supply chains, covering MCP servers and skills with checks for prompt injection, tool poisoning, toxic flows, and malware-laced skill files | |
| DScan | Open-source agent security suite for runtime tool-call tracing, prompt-injection shielding, MCP audits, adversarial testing, and sequence-level attack detection | |
| Sayfos SDK | Runtime guardrail SDK for AI agents with provenance checks, budget governance, plan preflight, and adjudication tokens before high-risk tool actions | |
| agent-sentinel | eBPF/BPF-LSM prototype that monitors local agent behavior and atomically blocks prompt-injection-driven access to sensitive files at the kernel boundary | |
| mcp-sploit | Metasploit-style framework for authorized security testing of MCP servers and MCP security gateways, including enumeration and exploit modules for unsafe tool exposure | |
| Clawvisor | AI agent gateway for purpose-based authorization, credential vaulting, and audit logging — agents declare task scope, humans approve once, Clawvisor enforces on every request without the agent ever seeing credentials | |
| trentclaw | Security assessment skill for OpenClaw environments: scans gateway config, skill permissions, MCP trust boundaries, and plugins, and correlates them into chained attack paths with severity-ranked remediation steps |
Agent Skill Specifications
| Specification | Org | Focus |
|---|---|---|
| AgentSkills.io | Open Standard | Agent skill definition and security requirements |
| Model Context Protocol (MCP) | Anthropic | Tool/resource integration protocol for LLMs |
| OpenAI Function Calling | OpenAI | Tool use specification for GPT models |
| Tool Use (Claude) | Anthropic | Claude's native tool use interface |
| LangChain Tools | LangChain | Tool abstraction for agent frameworks |
| AutoGPT Plugins | AutoGPT | Plugin system for autonomous agents |
| OpenAPI/Swagger | Linux Foundation | API specification commonly used as tool definitions |
Industry Reports & Blog Posts
- 🔗 Snowflake Cortex AI Escapes Sandbox and Executes Malware — PromptArmor, 2026. Prompt injection attack chain in Snowflake's Cortex Agent bypassed command allowlists via bash process substitution to achieve RCE; now patched.
- 🔗 Confused Deputy Attacks on Autonomous AI Agents — Cloud Security Alliance AI Safety Initiative, 2026. Research note on prompt injection chains enabling privilege escalation and autonomous compromise in AI agent systems.
- 🔗 How AI Assistants are Moving the Security Goalposts — Krebs on Security, 2026. AI agents as insider threats.
- 🔗 Hackers Used Meta’s AI Support Bot to Seize Instagram Accounts — Krebs on Security, 2026. Real-world incident where attackers socially engineered an AI account-recovery assistant into relinking target accounts, illustrating a new tool-mediated support-agent attack surface.
- 🔗 Anthropic: Challenges in Red Teaming AI Systems — Anthropic's perspective on evaluating agent safety.
- 🔗 OpenAI: Safety of Advanced AI Agents — Practices for governing agentic AI systems.
- 🔗 Compromising Agents via MCP — Invariant Labs deep-dive into MCP attack vectors.
- 🔗 Simon Willison: Prompt Injection Explained — Accessible introduction to prompt injection risks.
- 🔗 The sorry state of skill distribution — Trail of Bits, 2026. Demonstrates practical bypasses against ClawHub, Cisco skill-scanner, and skills.sh, showing how malicious skills can evade current marketplace scanners via truncation, archive indirection, poisoned bytecode, and prompt-injection framing.
- 🔗 TRAIL: Trusted Reasoning and AI Logging — Logging framework for auditable agent execution.
- 🔗 Cyber Threat Intelligence for AI Systems — AI-specific CTI framework with IoCs for supply-chain phases.
- 🔗 AI Safety Has 12 Months Left — Window to embed safety into infrastructure before market forces prevent it.
- 🔗 LiteLLM Hack: Were You One of the 47,000? — FutureSearch via Simon Willison, 2026. Analysis of PyPI supply-chain attack on LiteLLM: 47K downloads of exploited packages in 46 minutes, 88% of 2,337 dependent packages had unpinned versions.
- 🔗 Exploiting Agentic Browsers: From False Information to Cross-Site Data Leaks — Trail of Bits, 2026. Demonstrates lack of isolation in agentic browsers enabling attacks from false information dissemination to cross-site data leaks, resurfacing decades-old web vulnerability patterns.
- 🔗 OpenAI Help: Lockdown Mode — Simon Willison, 2026. Highlights OpenAI's new network-egress restriction mode for ChatGPT as a concrete mitigation for prompt-injection-driven data exfiltration in agentic workflows.
- 🔗 ClawHub by the Numbers: Metadata on All 52,652 Packages — Trent AI, 2026. Registry-wide metadata analysis of all 52,652 ClawHub packages finding only 22% meet a "clean" baseline; quantifies supply-chain risk across the OpenClaw skill ecosystem.
Related Awesome Lists
- awesome-llm-security — General LLM security resources.
- awesome-ai-safety — AI safety research and resources.
- awesome-chatgpt-prompts — Prompt engineering (includes adversarial examples).
- awesome-ml-for-cybersecurity — ML applied to cybersecurity.
- awesome-mcp-servers — MCP server ecosystem (attack surface reference).
- awesome-ai-agents — AI agent frameworks and projects.
Contributing
Contributions are welcome! Please read the contribution guidelines before submitting a pull request.
How to Contribute
- Fork the repository
- Add your resource in the appropriate category
- Use the format:
- 📄 **[Title](URL)** — Authors, Venue Year. One-sentence description. - Submit a pull request
Criteria
- Resources must be directly related to agent/tool/skill security
- Papers should be published or on arXiv
- Tools should be actively maintained (commits within last 6 months)
- Blog posts should provide substantial technical analysis
Citation
If you find this list useful in your research, please cite:
@misc{awesome-agent-skills-security,
author = {Liu, Yi},
title = {Awesome Agent Skills Security},
year = {2026},
publisher = {GitHub},
journal = {GitHub Repository},
howpublished = {\url{https://github.com/LLMSecurity/awesome-agent-skills-security}}
}
License
This list is released under CC0 1.0 Universal.
