git-workflow
Warn
Audited by Snyk on May 16, 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's hook and workflow scripts explicitly call GitHub (e.g., references/claude-code-hooks.md's merge-gate.sh and many pull-request/merge commands like
gh pr view,gh api, and checks for reviewThreads/annotations) which fetch and parse user-generated PR comments and API data and use that data to permit/deny actions, so untrusted third-party content from GitHub is read and directly influences tool use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata