resolve-pr-parallel

Warn

Audited by Snyk on Mar 3, 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 PR review threads (including comment "body") from GitHub via scripts/get-pr-comments (GraphQL/gh api) and then spawns pr-comment-resolver agents to read and act on those user-generated review comments (SKILL.md steps 1 and 3), so untrusted third-party PR comments could influence actions and inject instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 11:53 AM