The Agent Skills Directory

[SAFE]: The skill is purely instructional and defines a persona for reviewing specifications and code architectures. It explicitly states that the agent should not execute tasks or write code, focusing entirely on providing impartial advice and performing logic-based audits. No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected. The use of terms like 'CRITICAL' or 'BLOCK' refers to the structured output format the agent should use when communicating findings to the user and does not indicate any security risk within the skill itself.

the-consigliere