pr-summary
Warn
Audited by Snyk on Mar 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's script (scripts/pr-summary.sh) explicitly fetches open PR data from GitHub using
gh pr list --json, ingesting user-generated PR titles, branch names, authors and URLs which are displayed and used to drive grouping/formatting, so untrusted third-party content from GitHub is read and can influence the agent's output.
Audit Metadata