x-post-research

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

• Third-party content exposure detected (medium risk: 0.30). The skill collects public posts from X via the FxTwitter API and browser search, ingesting arbitrary outsider-authored social media posts and their content into the agent's workflow.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references https://api.fxtwitter.com/2/search?q=<URL-encoded-query>&feed=latest&count=100 as an operational search endpoint to collect public posts during runtime execution, making it an unverifiable external operational dependency with unknown/third-party provenance.