python-sdk
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 includes a RAG pattern and explicit web-search capabilities (references/agent-patterns.md and tool-builder internal_tools().web_search(True) and an app_tool "tavily/search-assistant@latest") which cause the agent to fetch and consume open web/search results (untrusted third-party content) as part of its workflow.
Audit Metadata