venice-responses

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly documents built-in web_search/web_scraping tools (e.g., adding {"type":"web_search"} to tools and venice_parameters.enable_web_search) and shows url_citation annotations and web_search_call output blocks, indicating the agent fetches and interprets public web content which can influence subsequent tool calls and behavior.