code-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: 0.80). The SKILL.md explicitly instructs in Full mode step 3 ("Best practices: Research patterns and idioms for the libraries/frameworks in use (use WebSearch/WebFetch as needed)") to fetch public web content, so the agent will ingest untrusted third-party webpages/search results and use them to influence its review and recommendations.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 07:29 PM