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-authoredSKILL.mdbodies 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” (thebodyfield printed/returned by_cmd_context/_cmd_read).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata