conductor-setup

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

• Third-party content exposure detected (low risk: 0.10). The workflow downloads third-party skills from arbitrary URLs specified in the catalog, ingesting external code and free text into the agent runtime.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to download external skills from GitHub raw URLs using curl, introducing a weak runtime external dependency on arbitrary third-party repositories.