search
Warn
Audited by Snyk on Sep 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to actively search and fetch public web pages, search results, and documentation via WebSearch, WebFetch, and various MCP search/research tools, which is a low-risk active fetch pattern.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata