x-api

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly instructs fetching public, user-generated content from X/Twitter API endpoints (e.g., https://api.x.com/2/tweets/... and the tweets/search/recent endpoints), so the agent would ingest untrusted third-party posts that could contain instructions affecting behavior.