ljg-card

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

• Third-party content exposure detected (low risk: 0.10). The required workflow ingests user-provided web pages via a URL reading tool and pasted text inputs, exposing the agent to outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The asset templates load Google Fonts via an external URL (https://fonts.googleapis.com/css2?...), constituting an external runtime operational dependency with uncontrolled remote provenance.