web-search
Warn
Audited by Snyk on Mar 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill calls TavilyClient.search to fetch web and news results and returns the third-party 'content' bodies (scripts/search.py and SKILL.md describe using Tavily for web/news searches), so it ingests untrusted public web content that the agent would read and could influence actions.
Audit Metadata