changelog-draft
Warn
Audited by Snyk on May 18, 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 fetches PR bodies, files, and issue data directly from GitHub via the gh CLI (see SKILL.md Step 2 and scripts/fetch_prs.py, fetch_issue_reporters.py, classify_contributors.py), which are untrusted, user-generated third‑party contents that the agent parses and uses to decide changelog entries, inclusion, and attributions—allowing those external texts to materially influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata