The Agent Skills Directory

[NO_CODE] (SAFE): The skill consists entirely of Markdown documentation and code examples (SQL, TypeScript, JSON) intended for reference. There are no shell scripts, Python scripts, or Node.js executables that would run on the agent's host system.
[SAFE] (SAFE): No malicious patterns were detected across any of the 10 threat categories. The skill does not attempt to access sensitive files, perform network operations, or use prompt injection techniques to bypass agent safety filters.
[CREDENTIALS_UNSAFE] (SAFE): While the code snippets mention authentication (JWT), they use variable placeholders like 'SECRET' rather than hardcoding actual sensitive credentials or private keys.

backend-development