subagent-pipeline
Warn
Audited by Snyk on Aug 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In SKILL.md’s subagent-pipeline, the Fixer subagent explicitly reads review comments from GitHub at runtime via
gh api repos/.../pulls/.../comments, where those comments include free text authored by outsiders (e.g., non-first-party PR comment authors).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata