reproduce-bug
Warn
Audited by Snyk on Apr 2, 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). This skill explicitly fetches and reads GitHub issue bodies and comments using "gh issue view" (see SKILL.md "Fetch the issue" and "Extract key details / Read the issue and comments"), which are public user-generated contents the agent will interpret and then act on (e.g., follow reproduction steps and drive browser automation), creating a clear avenue for indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata