agency-docs-updater

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

• Third-party content exposure detected (medium risk: 0.30). The workflow consumes Fathom transcripts, Zoom transcripts, and meeting summaries which originate from external meeting platforms containing participant-submitted free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). An inbound operational dependency points to GitHub URLs for remote code repositories (glebis/claude-skills and glebis/youtube-uploader) that are fetched or cloned during setup and runtime to execute skills and publishing scripts, representing an unofficial external source with medium tier provenance.