The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a variety of shell commands to audit the local environment for security threats.
Evidence: Employs find, grep, ps, netstat, pgrep, and crontab within SKILL.md to identify malicious files, active crypto miners, and persistence mechanisms.
[DATA_EXFILTRATION]: Accesses sensitive configuration and system files to evaluate the project's security posture.
Evidence: Reads project .env files and system files such as /etc/sudoers to detect potential credential leaks or privilege misconfigurations. The skill includes logic using sed to mask sensitive values before they are displayed to the user.

security-audit