The Agent Skills Directory

[SAFE]: The skill is entirely composed of Markdown guidelines, YAML configuration, and JSON evaluation data. There are no scripts (.py, .js, .sh), executables, or binary files included.
[SAFE]: No network operations or external data fetching mechanisms (such as curl, wget, or API requests) are present in the instructions or workflows.
[SAFE]: Analysis of all files reveals no hardcoded credentials, sensitive file path access (e.g., .ssh, .aws), or attempts to exfiltrate environment variables.
[SAFE]: No obfuscation techniques, such as Base64 encoding of commands, zero-width characters, or homoglyph attacks, were detected.
[SAFE]: The skill does not attempt to acquire elevated privileges, establish persistence, or execute dynamic code at runtime.

contrast-framing