The Agent Skills Directory

[SAFE]: The skill consists of instructional markdown and YAML configuration for performing security audits. It does not include executable code, scripts, or binary files.
[COMMAND_EXECUTION]: The instructions direct the agent to utilize standard security audit tools like npm audit, pip-audit, and cargo audit to evaluate the dependency security of an audited project. These are well-known industry-standard tools, and their use is consistent with the skill's primary purpose.
[DATA_EXFILTRATION]: While the skill includes checklists for identifying sensitive data (e.g., credentials, PII, API keys), these are for the purpose of auditing a target application. The skill does not perform any unauthorized access, collection, or transmission of data from the host environment.
[PROMPT_INJECTION]: The skill does not contain patterns associated with prompt injection, safety filter bypasses, or instruction overrides. It provides clear, structured guidance for an agent to follow.

security-review