The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions focused on coding style, structural organization, and naming conventions. There are no executable scripts or commands.
[SAFE]: The instructions explicitly advocate for security best practices under the 'Quality bar' section, specifically mentioning input validation, prevention of injection, and avoiding hardcoded credentials.
[SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or remote code execution was found. The skill operates purely within the context of the agent's code generation logic.

coding-principles