layer2

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches an arbitrary web page containing markdown documentation from an external URL.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches behavior-selecting instructions from an external URL with unknown personal or third-party provenance, constituting a weak operational dependency.