labarchive-integration

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads notebook entries and comments from LabArchives via API, which can contain outsider-submitted research data and notes.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill installs an unofficial third-party Python package from a personal GitHub repository (https://github.com/mcmero/labarchives-py) at runtime, introducing an unverified external dependency with weak provenance.