ask-matt
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). SKILL.md describes workflows like
/triageand/wayfinderthat operate on “issues” from an external issue tracker, and at runtime those issue body texts (outsider-authored) would be ingested into the agent’s LLM context to drive/implement.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata