web-search-researcher
Warn
Audited by Snyk on Feb 16, 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 explicitly uses WebFetch/WebSearch to retrieve and analyze content from open web sources (e.g., Stack Overflow, GitHub issues, public blogs and forums) and instructs the agent to read and quote that user-generated third-party content, creating exposure to indirect prompt injection.
Audit Metadata