cloud-api-operations

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

• Third-party content exposure detected (low risk: 0.10). The required workflow directs the agent to fetch SDK source code repositories and official documentation pages from third-party platforms (GitHub, Gitee, CNB) during API discovery.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references an external documentation index URL at setup/runtime (https://docs.cloudbase.net/ai/cloudbase-ai-toolkit/api-reference.md) to resolve Tencent Cloud API actions, which constitutes an operational dependency.