skill-router

Warn

Audited by Snyk on Jul 7, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.75). Yes: the required runtime workflow runs python scripts/skill_index.py context ... / read ..., which reads outsider-authored SKILL.md bodies from local roots like ~/.agents/skills/ / ~/.codex/skills/ / plugin caches and injects that free text into the agent’s LLM context via the “skill context packet” (the body field printed/returned by _cmd_context / _cmd_read).

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 7, 2026, 06:43 AM
Issues
1
Security Audit — snyk — skill-router