osint

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

• Third-party content exposure detected (low risk: 0.10). The OSINT agent actively fetches arbitrary web pages, social media profiles, and search results via external APIs (Jina, Tavily, Exa, Perplexity, Apify, Bright Data) which ingest outsider-authored free text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The referenced GitHub repository https://github.com/apify/agent-skills is an unverified, user-selected third-party personal/community repository without official first-party binding or authenticated integrity checks, and it acts as an operational dependency by supplying embedded code (run_actor.js) that is executed at runtime.