branch-finish
Warn
Audited by Snyk on Feb 21, 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). Yes — the skill fetches remote repository data and inspects GitHub PRs (see the check_pr_status function using git fetch origin and gh pr view/gh pr list), which ingests untrusted, user-generated third-party content that the workflow reads and uses to decide merges and cleanup.
Audit Metadata