The Agent Skills Directory

[SAFE]: The skill contains only instructional text and reference material for performing security audits. It does not include any executable code, shell scripts, or external network requests.
[INDIRECT_PROMPT_INJECTION]: By design, the skill involves processing untrusted external source code (the audit target). This represents an attack surface where a malicious codebase could attempt to influence the auditing agent. However, the instructions themselves are static and do not facilitate this; the risk is inherent to the auditing task itself and is considered low risk.

network-security-check