The Agent Skills Directory

[SAFE]: The skill provides defensive guardrails and security auditing functionality consistent with its stated purpose.
[COMMAND_EXECUTION]: The security-audit.mjs script utilizes the Node.js child_process.execSync module to execute local system commands including find, git, lsof, chmod, fdesetup, and lsblk. These commands are used to inspect file permissions, git history, and system configurations for security vulnerabilities.
[DATA_EXPOSURE]: The skill scripts access sensitive filesystem locations (e.g., ~/.ssh/, .env files, and wallet configuration paths) to verify they are properly secured. Findings are logged to the local terminal for the operator's review, and no network operations are present to exfiltrate this data.

agent-security