GitHub Workflow
Warn
Audited by Snyk on Mar 10, 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 explicitly fetches and interprets user-generated GitHub content (issues, PRs, review comments, commits) via gh commands and MCP calls (e.g., "gh api repos/{owner}/{repo}/pulls/$PR_NUM/comments", "gh pr list --json ...", and scripts like scripts/release-notes.sh and scripts/activity-summary.sh), and those comments/bodies are used to suggest or apply fixes and drive actions (e.g., apply fixes, commit, merge), so untrusted third-party content can materially influence tool use and next actions.
Audit Metadata