motion-explainer

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

• Third-party content exposure detected (low risk: 0.10). The skill workflow involves web searching in step 1 ("搜尋主題的最新資料"), but this is an active search/fetch action initiated by the agent rather than monitoring an outsider-submitted feed.

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

• Potentially malicious external URL detected (high risk: 0.70). The script fetches fonts via curl from GitHub and npm repositories during setup, constituting an operational inbound remote dependency with weak provenance.