check
Warn
Audited by Snyk on May 20, 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's Triage Mode and PR handling explicitly fetch and process public, user-generated GitHub content (e.g., using
gh issue list -R,gh pr list -R,gh pr viewand related flows described in SKILL.md) and then reads/interprets that content to decide and perform actions (close, comment, merge, push), so untrusted third-party issue/PR text could influence tool use and behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata