performance-testing-review-ai-review
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). This skill pulls arbitrary pull request diffs from GitHub (e.g., get_pr_diff, GitHub Actions checkout and GitHub API usage) and injects that user-generated content directly into LLM prompts (ai_review / review_prompt), exposing the agent to untrusted third‑party content that could carry indirect prompt injection.
Audit Metadata