convez.ai
MCP ServerSegurançaIntermediário
cognis-digital

RAGShield

cognis-digital/ragshield

Detector de poisoning em RAG — anomalias de embedding e backdoors

Ver no GitHub
BomPluginScore · de 0 a 100

Detector de envenenamento de corpus RAG que identifica anomalias em embeddings e triggers de backdoor em bases de conhecimento. Funciona como MCP server integrado ao Claude Desktop e agents, oferecendo relatórios em múltiplos formatos (tabela, JSON, SARIF, HTML) para workflows de segurança.

Instalação

$npx convez-ai cognis-digital/ragshield

1 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

Estrelas
1
Forks
0
Acompanhando
0
Saúde
100%
Último commit
há 4 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Auditar bases de conhecimento corporativas antes de usar em RAG
  • Detectar injeção de conteúdo malicioso em corpora de documentos
  • Integrar verificação de segurança em pipelines CI/CD de LLMs
  • Investigar anomalias em vetores de embedding de datasets

Veredito

Ferramenta especializada e bem-arquitetada para um problema real em RAG systems. Integração MCP nativa permite automação em agents; relatórios em SARIF/HTML são práticos para compliance. Produto maduro dentro de nicho técnico específico de segurança de LLMs.

README

A tradução para o português deste README ainda está na fila.

RAGSHIELD — RAG corpus poisoning detector — embedding anomalies, backdoor triggers

Part of the Cognis Neural Suite by Cognis Digital Cognis Open Collaboration License (COCL) v1.0 · domain: ai-security

PyPI CI License: COCL 1.0 Suite

RAG corpus poisoning detector — embedding anomalies, backdoor triggers.

AI Security & Governance — securing LLMs, agents, and the MCP supply chain.

Why

Security and intelligence teams need RAG corpus poisoning detector — embedding anomalies, backdoor triggers without standing up heavyweight infrastructure. ragshield is single-purpose, scriptable, CI-friendly, and self-hostable: point it at a target, get prioritized findings in the format your workflow already speaks (table, JSON, SARIF, HTML), and wire it into agents over MCP when you want it autonomous.

Install

pip install cognis-ragshield
# or, from this repo:
pip install -e ".[dev]"

Quick start

ragshield --version
ragshield scan demos/                      # run against the bundled demo
ragshield scan demos/ --format sarif --out r.sarif --fail-on high
ragshield scan demos/ --format html --out report.html
ragshield mcp                              # expose as an MCP server (Cognis.Studio / Claude Desktop / Cursor)

Built-in demo scenarios

Each scenario folder includes a SCENARIO.md describing the situation and the findings to expect.

Output formats

  • Table (default) — human-readable terminal summary
  • JSON — machine-readable findings for pipelines
  • SARIF — drops into GitHub code-scanning / IDE problem panes
  • HTML — shareable report with severity rollups

How it fits the Cognis Neural Suite

ragshield is one of 52 tools in the Cognis Neural Suite. Every tool ships an MCP server, so Cognis.Studio agents can call them as scoped capabilities.

Sibling tools in ai-security: aegis, promptmirror, ledgermind, adversa, guardpost, hallumark, aicard, biascope, mcpharden, agentlog

Architecture & roadmap

Contributing

PRs, new detections, and demo scenarios are welcome under the collaboration-pull model. See CONTRIBUTING.md and SECURITY.md.

License

Source-available under the Cognis Open Collaboration License (COCL) v1.0 — free for personal, internal-evaluation, research, and educational use; commercial / production use requires a license (licensing@cognis.digital). See LICENSE.

Responsible use

This is dual-use security software. Use it only against systems, data, and identities you own or are explicitly authorized in writing to test, and in compliance with applicable law.

About

Cognis Digital — Wyoming, USA · Making Tomorrow Better Today: Advanced Cybersecurity, AI Innovation, and Blockchain Expertise.

Ver o original no GitHub

Bom para

Relacionados