ask-many-models

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly runs "Deep Research" queries that use web-search tools and background research APIs (see SKILL.md "Deep Research" section and scripts/deep-research-query.ts which calls OpenAI/Gemini deep research with web_search and returns citations/URLs, and scripts/query.ts which attaches provider web_search/url_context tools), so it fetches and ingests untrusted public web content that is then read and synthesised as part of the workflow.