validation-doctor
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 explicitly calls brave_web_search to retrieve open web search results and even permits a fetch fallback for Chrome probes, so the agent ingests untrusted public web content as part of its diagnostic workflow.
Audit Metadata