github-pr-agent-workflows
Warn
Audited by Snyk on May 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: 0.90). The skill's bundled scripts (scripts/pr-review-summary.sh and scripts/wait-pr-review.sh) use
gh api graphqlto fetch PR review threads and comment bodyText from GitHub—user-generated, potentially public content—which SKILL.md and the decision rules require the agent to inspect and act on (e.g., whether to edit, wait, or merge), so third-party content can materially influence agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata