code-review
Warn
Audited by Snyk on Apr 28, 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 reads untrusted, user-generated GitHub content (PR title/body via
gh pr view --json title,body, diffs viagh pr diff/git diff, and "read the full file(s)" in step 4 of SKILL.md) and uses that content to drive reviewers' decisions and comments, so third-party text could inject instructions that materially influence the agent's actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata