gh-stack
Warn
Audited by Snyk on Aug 5, 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). Skill reads outsider-authored free text at runtime via
gh stack view --json/viewand other GitHub-fetching commands that pull PR metadata (titles/bodies/state) from GitHub into the agent’s LLM inputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata