resolve-pr-parallel
Warn
Audited by Snyk on Mar 2, 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). This skill fetches and ingests user-generated GitHub PR review comments (see scripts/get-pr-comments which queries comment bodies via the GitHub GraphQL API) and then spawns pr-comment-resolver agents (SKILL.md step 3) that are expected to read and act on those comment bodies, so untrusted third-party content can directly influence agent actions.
Audit Metadata