status
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: 0.70). SKILL.md requires scanning and parsing roadmap and ADR files from
docs/roadmap/anddocs/adr/at runtime, which are outsider-authored free text if the operating user did not author those documents (e.g., repo content from other contributors), and that text is ingested into the LLM context via the agent’s file reading/parsing.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata