extract
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: 1.00). This skill calls Tavily's extraction API (POST https://api.tavily.com/extract) to fetch and return content from arbitrary user-supplied URLs via the "urls" request field, exposing the agent to untrusted public web content that could contain indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill makes runtime calls to https://api.tavily.com/extract to fetch arbitrary pages' raw_content which is injected into the agent context and can therefore directly influence/control prompts or instructions.
Audit Metadata