The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard Unix commands such as grep and find to perform local analysis of the codebase. These commands are used to identify hardcoded secrets, unsafe code patterns, and project structure metrics. All operations are confined to the local project directory.- [EXTERNAL_DOWNLOADS]: The skill references standard auditing tools like npm audit, pip-audit, cargo audit, and govulncheck. These tools are used to check for known vulnerabilities by querying official, well-known package registries. The use of npx for tools like madge is a standard practice for running Node.js utilities.- [SAFE]: The overall behavior of the skill is consistent with its stated goal of providing a codebase health assessment. It does not attempt to exfiltrate data to untrusted domains, gain persistent access, or bypass security constraints. The scanning for hardcoded secrets is the intended purpose and does not constitute a vulnerability within the skill itself.

audit-codebase