code-review-ai-ai-review

Fail

Audited by Snyk on Nov 13, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate code-review guide, but its complete example prints "Posted review" without calling the GitHub API, which misreports a limitation in a way that could mislead a user, though this reads as a careless stub rather than intent to harm.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). The required CI workflow automatically triggers on every pull_request event and feeds the PR description and diff into the AI review prompt, and outsiders can open PRs against public repos without the agent selecting them.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 13, 2026, 08:30 AM
Issues
2