browse-x

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

• Third-party content exposure detected (medium risk: 0.30). The skill reads public X (Twitter) posts, search results, and user profiles via an API bridge, which ingest outsider-authored social media content at runtime.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill makes runtime HTTP requests to an unauthenticated external service at x.pcstyle.dev (configured as the default API base), introducing an unverifiable third-party operational dependency with unknown publisher provenance.