Skip to content

Security: amurlaniakea/agent-fixer-stage

Security

SECURITY.md

Security Policy

Supported Versions

Version Supported
0.2.0 Yes
0.1.0 Yes

Reporting a Security Vulnerability

If you discover a security vulnerability in Agent Fixer Stage, please report it responsibly.

Do NOT open a public GitHub Issue for security vulnerabilities.

Instead, report via email:

You will receive a response within 48 hours.

Security Considerations

Agent Fixer Stage is a defense tool, but has limitations:

Layers (v0.2.0)

  • Layer 0 (Normalization): Unicode NFKC + homoglyph detection + leetspeak map. Covers common evasion techniques.
  • Layer 1 (Pattern Matching): 80 patterns (EN, ES, FR, DE, IT, PT) with weighted scoring. 3 passes (normal, leetspeak variants, cross-line).
  • Layer 2 (Embeddings): TF-IDF + cosine similarity with 33 malicious examples. Semantic detection.
  • Layer 2.5 (Scope Drift): TF-IDF cosine similarity between scope and output. Detects off-topic outputs.
  • Layer 3 (LLM Judge): Optional LLM-based consistency check (Ollama or remote API).
  • MCP Integration: DefensePipeline for tool audit + output audit combination.

Estimated Detection

  • Global: ~90-95% of common attacks (multi-language, multi-layer).
  • Not 100% — sophisticated attackers with knowledge of patterns can design evasions.

Known Limitations

  • TF-IDF embeddings son menos precisos que modelos transformer para similitud semántica.
  • LLM Judge requiere Ollama ejecutándose localmente o API key para remoto.
  • Scope Drift Detection con TF-IDF es vulnerable a padding attacks (repetir scope para evadir). Mitigation: usar mode=full para alta seguridad.
  • Pattern matching solo cubre firmas de ataque conocidas en 5 idiomas.
  • Zero-width chars como separador inter-palabra ahora se detectan, pero pueden existir otras técnicas de colisión.
  • LLM Judge es fail-open: si el servicio no disponible, retorna consistent=True por diseño. El Fixer NO es un single point of failure — Capas 1 y 2.5 proveen defensa base.

Use Agent Fixer Stage as one layer in a defense-in-depth strategy. It is not a silver bullet.

Dependencies

No runtime dependencies (Python stdlib only). Dev: pytest, black, ruff, mypy, pytest-cov Optional: requests (for LLM judge remote mode)

There aren't any published security advisories