web-research
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 spawns research subagents that use the web_search tool (Tavily) and fetch_url to gather web pages and source URLs from the open web, and the agent is instructed to read and synthesize those external findings—exposing it to untrusted, user-generated third-party content.
Audit Metadata