The Agent Skills Directory

[SAFE]: The skill serves as a legitimate technical guide for the 'sunpeak' testing framework. It describes standard developer workflows including scaffolding test directories, cloning example code from the official Sunpeak GitHub repository, and running tests via a CLI.
[DATA_EXPOSURE_&_EXFILTRATION]: The skill mentions using .env files for managing API keys for LLM evaluations. It correctly identifies these files as gitignored and provides standard practices for secret management. No hardcoded credentials or access to sensitive system paths (like SSH keys) were detected.
[EXTERNAL_DOWNLOADS]: The skill provides instructions to clone reference code from 'github.com/Sunpeak-AI/sunpeak'. As Sunpeak-AI is the author and a known entity in this context, this is a standard vendor-provided resource. It also references well-known packages from established registries (e.g., @ai-sdk/openai) which is expected for its functionality.
[COMMAND_EXECUTION]: The commands described (e.g., sunpeak test, sunpeak inspect) are specific to the framework's testing and debugging capabilities. There are no instances of privilege escalation (sudo) or dangerous shell piping patterns.
[PROMPT_INJECTION]: No instructions were found that attempt to bypass AI safety guidelines or override agent behavior. The text uses neutral, instructional language for developers.

test-mcp-server