python-executor

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

• Third-party content exposure detected (low risk: 0.10). The required workflow has the agent write and run Python that can fetch arbitrary web pages (the Web Scraping and API Calls examples, triggered by "web scraping"), so outsider-authored page text reaches the LLM only after the agent chooses to fetch it, which makes this low rather than medium.