agora

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly performs runtime fetches of external docs (starting with https://docs.agora.io/en/llms.txt and then fetching the matched markdown/OpenAPI URLs on docs-md.agora.io such as https://docs-md.agora.io/api/conversational-ai-api-v2.x.yaml) and requires those fetched documents to build request schemas and agent behavior, so remote content fetched at runtime can directly control the agent's prompts/responses.