cloud-functions
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: Static detector flags regarding concealment were evaluated as false positives. The instructions provided are security best practices designed to prevent sensitive credentials from being recorded in chat logs or tool call history, and to provide automated deployment status polling for a better user experience.
- [DATA_EXFILTRATION]: The skill implements robust data protection protocols, explicitly forbidding the return of sensitive runtime data (such as temporary credentials, platform headers, or environment variables) in function responses. It directs the agent to follow a specific 'Sensitive Runtime Data Protection' protocol.
- [CREDENTIALS_UNSAFE]: The instructions prioritize secure secret management, recommending the use of environment variables, server-side API keys, and Tencent Cloud key pairs rather than hardcoding credentials in source code. It includes guidance on merging credentials into existing configurations safely to avoid accidental overwrites.
- [COMMAND_EXECUTION]: All command execution and tool usage, including MCP tools like manageFunctions and the callCloudApi fallback, are directed toward the official Tencent CloudBase platform. These operations are within the primary functional scope of the skill for cloud resource management.
Audit Metadata