autonomous-dev
Warn
Audited by Snyk on Mar 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and parse user-generated GitHub content (issue bodies, PR inline comments, review threads and bot reviews) via gh api/CLI calls as part of its autonomous workflow (see references/autonomous-mode.md and references/review-commands.md), so untrusted third‑party text can directly influence decisions and actions like applying patches, cherry-picks, and triggering reviews.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata