web-research
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). The skill explicitly spawns subagents that use the web_search tool (Tavily) and the fetch_url tool to retrieve and save content from arbitrary public websites/URLs, and those findings are read and synthesized by the agent, exposing it to untrusted third-party/user-generated content.
Audit Metadata