changelog
Warn
Audited by Snyk on Feb 25, 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.md explicitly says it "Uses GitHub API to get all PRs merged to main since last changelog," meaning the agent fetches user-generated PR titles and descriptions from GitHub (an open third‑party source) and reads/interprets them to decide changelog content, which could allow indirect prompt injection.
Audit Metadata