extract-wisdom

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads external web pages via WebFetch and arbitrary YouTube transcripts via yt-dlp, but does not monitor or consume an outsider-submitted queue, feed, or monitored inbox.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill contains an explicit runtime remote dependency pointing to https://mermaid.ink/img/ which is fetched via urllib.request.urlopen during diagram rendering, possessing weak/unknown external provenance.