gh-daily
Warn
Audited by Snyk on Mar 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and ingests user-generated GitHub content (issues, PRs, notifications) via the gh CLI in "Phase 3: Gather Activity Data" (e.g.,
gh issue list,gh pr list,gh api notifications) and then instructs subagents in "Phase 4" to read/classify and act on that content, so untrusted third‑party text can materially influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata