get-info
Warn
Audited by Snyk on Aug 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In SKILL.md Step 2, the agent calls the Exa MCP tool (
web_search_exa) using a query built directly from outsider-suppliedtopic/timespan, which causes it to ingest free-text content returned by Exa (e.g., “Title/Published/Highlights”) and then summarizes that content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata