companion

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches a curriculum manifest from an external URL (https://agency-lab.glebkalinin.com/api/curriculum/<cohort>.json), which is user/outsider-accessible data retrieved via an active fetch.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs fetching a curriculum JSON manifest from an external URL during execution, creating an operational inbound dependency on an unofficial/unknown third-party host.