release
Warn
Audited by Snyk on Mar 1, 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.md "4. Closing Issue の収集" step explicitly runs
gh pr view ...to fetch PR bodies (user-generated GitHub content) and parses those bodies to decide which issues to include/close and to populate PR text, so untrusted third-party content can influence agent actions.
Audit Metadata