cro

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

• Third-party content exposure detected (low risk: 0.10). The skill processes marketing pages, forms, and URLs provided by the user during a conversion rate optimization task, which is an active search/fetch of user-supplied URLs.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references an external GitHub URL for an inbound routing playbook, meeting the dependency gate criteria under a reputable unofficial provenance tier.