x-api

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly reads public, user-generated X/Twitter content (see SKILL.md "Core Operations" like "Search Tweets" at https://api.x.com/2/tweets/search/recent and "Read User Timeline" at https://api.x.com/2/users/{user_id}/tweets) and uses that content as part of its workflow (searching, analysis, or generating/posting content), so untrusted third‑party posts could influence agent decisions.