external-repo-guidelines
Warn
Audited by Snyk on Jun 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill reads upstream repository contributing guideline files (e.g., AGENTS.md/CONTRIBUTING.md/.github/CONTRIBUTING.md) from a fork-mode external repo, so at runtime it can ingest outsider-authored free text from those documents into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata