triage
Warn
Audited by Snyk on Mar 29, 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 ingests user-generated GitHub issue and PR content (see "Phase 1 — Issue Intake" commands like
$GH issue view ... --json ... body,commentsand PR diff fetching), and it requires the agent to read and act on that untrusted third-party content when classifying, proposing fixes, and drafting/posting comments, so it can enable indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata