The Agent Skills Directory

[COMMAND_EXECUTION]: The script risk-analyze.js executes several git commands (rev-parse, diff, status, log) and grep to perform its analysis. These commands are executed locally using a utility that takes arguments as an array, minimizing the risk of command injection.
[DATA_EXPOSURE]: The skill reads project files, including configuration files like .env, package.json, and tsconfig.json, to detect the removal of exports or configuration keys. It only reports the metadata (e.g., the name of a removed key) and does not extract or exfiltrate the values contained within these files.
[SAFE]: No malicious patterns such as remote code execution, obfuscation, or persistence mechanisms were detected. The skill's behavior is consistent with its stated purpose of providing code change risk metrics.

risk-assess