The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute grep commands (e.g., grep -r "req\.\(body\|params\|query\)") to perform static analysis on source code files. These commands are non-destructive and essential to the skill's stated purpose of auditing code for vulnerabilities.
[DATA_EXPOSURE]: The audit protocol includes searching for hardcoded credentials and secrets within the analyzed codebase. This is a diagnostic step intended to improve the security of the user's code and does not involve exfiltrating data to external sources.
[PROMPT_INJECTION]: The skill adopts a professional persona with detailed instructions. There are no attempts to bypass model safety guidelines or override systemic constraints.

security-sentinel