labarchive-integration

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

• Third-party content exposure detected (medium risk: 0.30). The workflow accesses LabArchives electronic lab notebooks, which can contain user-created entries and comments from various contributors, introducing an indirect prompt injection risk via notebook content retrieval.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs installation of a third-party package directly from an arbitrary GitHub repository (https://github.com/mcmero/labarchives-py), which constitutes an unverifiable runtime external dependency under common/reputable unofficial provenance.