lov-describe-image

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

• Potentially malicious external URL detected (high risk: 0.80). The skill's runtime script calls the external model endpoint https://open.bigmodel.cn/api/paas/v4/chat/completions (BASE_URL) to retrieve model-generated text which is printed/forwarded as the skill's output, meaning remote content is fetched at runtime and directly controls the agent's responses.