review

Warn

Audited by Snyk on Mar 4, 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 fetches and ingests user-generated GitHub PR content (reviews, inline review comments, review threads, and CI logs) via scripts (scripts/fetch-pr-feedback.sh and scripts/investigate-ci-failures.sh) and the SKILL.md workflow requires the agent to read/assess that content and act on it (implement fixes, resolve threads, push changes), so untrusted third‑party comments could materially influence tool use and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 08:52 AM