jb-skill-prefs

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

• Third-party content exposure detected (low risk: 0.10). This skill’s required runtime workflow reads a first-party GitHub Gist’s content (gh gist view ... --filename jb-skill-preferences.json5 and jb-skill-preferences-setup.md) and edits it, but it does not describe ingesting outsider-authored free text from any user-controlled queue/feed that the workflow monitors without first selecting a specific entry.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches and reads the remote Gist at https://gist.github.com/bjesuiter/98d5768dc360093affb8d8fdb064e45f at runtime (via gh gist view) and relies on its registry and setup markdown to control install/update behavior, so this external content directly controls agent instructions.