x-top-account

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

• Third-party content exposure detected (medium risk: 0.30). The agent skill fetches external X (Twitter) account ranking data, including public profile biographies and titles, via an API from RedFox Hub (redfox.hk), which ingests outsider-authored free text into the runtime workflow without prior item selection.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill injects an unversioned CDN script tag pointing to https://cdn.jsdelivr.net/npm/html2canvas@1.4.1/dist/html2canvas.min.js into generated HTML reports at runtime, establishing a weak/unknown third-party operational dependency.