web-search
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). This skill programmatically fetches and returns external web content (scripts/web_search.py calls the DuckDuckGo API at https://api.duckduckgo.com and the Tavily endpoint https://api.tavily.com/search as shown in references/search_methods.md), exposing the agent to untrusted, third-party result snippets and URLs that it is expected to read and use.
Audit Metadata