xy-replica

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

• Third-party content exposure detected (low risk: 0.10). The workflow takes video files, transcripts, or links from the user to deconstruct structural formulas and generate replica scripts, meaning it does not automatically consume untrusted external feeds or outsider-authored submissions without the agent first selecting a specific item.

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

• Potentially malicious external URL detected (high risk: 0.70). The script connects to a remote API endpoint (api.xyskill.xyz) at runtime to fetch data that governs behavior, establishing an unverifiable operational dependency with weak/unknown provenance.