session-start
Warn
Audited by Snyk on Feb 15, 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 fetches and reads user-generated GitHub content (project items and fields via
gh project item-list/GH_CACHE_ITEMS, PR bodies viagh pr list, and instructs to "Read the issue - Full description and all comments"), which are open/public/untrusted third-party sources and thus could carry indirect prompt injection.
Audit Metadata