ant-design

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

• Third-party content exposure detected (low risk: 0.10). The skill references an external URL for fetching design catalog updates (https://api.agent-ds.oday-bakkour.com/...), which represents optional fetching of external content under user or agent discretion.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill contains an external URL https://api.agent-ds.oday-bakkour.com/... used in an instruction to fetch live catalog updates at runtime, representing a weak/unknown/suspicious operational dependency.