The Agent Skills Directory

[SAFE]: The skill is a documentation-oriented guide for configuring AI agents with security best practices. It does not contain executable malicious scripts or instructions.
[SAFE]: References to dangerous system commands like rm -rf /, sudo, and chmod 777 are explicitly used as examples for 'Security Hooks' intended to block or warn against such actions.
[SAFE]: The policy reinforces industry-standard security practices by explicitly forbidding the hardcoding of API keys or the committal of .env files and other secrets to version control.
[EXTERNAL_DOWNLOADS]: The skill suggests using security auditing tools such as cc-safe via npx. This involves downloading and running code from the official NPM registry, which is a standard development practice for security analysis.

agent-configuration