ai-code-generation

Warn

Audited by Snyk on Feb 15, 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's reviewPullRequest implementation uses Octokit to fetch pull request files and file contents from GitHub (owner/repo/pr), then feeds those user-generated/public code files into the LLM for review, which clearly ingests untrusted third‑party content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:48 PM