python-sdk

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's docs and reference workflows explicitly show agents using web search and browser automation to fetch and use open web content (see references/agent-patterns.md RAG pattern using "tavily/search-assistant@latest", references/sessions.md "browser-automation" example, and references/files.md "Working with URLs"), meaning the agent ingests untrusted public third‑party content that can influence its actions.