auto-mcp
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows secure instruction principles and does not exhibit malicious patterns. It acts as an orchestrator for creating specific functionality based on user needs.
- [COMMAND_EXECUTION]: The skill includes guidelines for generating tools that interact with the system shell. It mandates security best practices, such as requiring hardcoded allowlists and prohibiting the use of shell execution with dynamic input to mitigate injection risks.
- [EXTERNAL_DOWNLOADS]: The instructions reference official SDKs and common, reputable libraries (e.g., Anthropic Claude Agent SDK, requests, and zod) for implementation. These are standard dependencies for the tasks described.
- [CREDENTIALS_UNSAFE]: The skill actively enforces secret management best practices by instructing the agent to never hardcode API keys or tokens and instead use environment variables.
Audit Metadata