feature-intake
Warn
Audited by Snyk on Jun 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill explicitly reads existing GitHub issue/project-board state (titles/bodies/comments/fields) via
gh issue list ... --json ... projectItemsandgh project ...during duplicate/nearby-work checks, and those bodies/comments are outsider-authored free text that can be ingested into the agent’s LLM context for analysis (even though it says to treat them as untrusted).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata