The Agent Skills Directory

[COMMAND_EXECUTION]: The helper script scripts/check-patcher.mjs uses spawnSync to invoke standard ecosystem security tools such as npm audit, pip-audit, govulncheck, cargo audit, and trivy. This is a core functional requirement of the scanner.
[DATA_EXFILTRATION]: The scanning logic in scripts/check-patcher.mjs includes a routine to detect committed sensitive files like .env to alert the user of potential secret exposure. The script does not exfiltrate this data; findings are reported locally.
[REMOTE_CODE_EXECUTION]: The skill's instructions guide the agent to identify and remediate dangerous patterns such as curl | sh or wget | sh within the user's project to improve overall security posture.
[SAFE]: The skill follows established security best practices, uses trusted ecosystem tools, and provides clear verification playbooks. No obfuscation or malicious redirection patterns were detected.

patcher