load-pr-review

Warn

Audited by Snyk on Mar 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: 1.00). The skill explicitly fetches GitHub PR review threads and comment bodies from third-party sources (see SKILL.md "Step 1: Fetch Review Comments" and references/api-contract.md) and the workflow (Plan/Fix modes in SKILL.md and scripts/load-pr-review.js) requires the AI to read and classify those user-generated comments and act on them (apply fixes and perform writeback), so untrusted third-party content can materially influence agent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 06:41 AM