The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains instructions designed to override the agent's default behavior and influence its internal reasoning process (e.g., "In your internal reasoning act as if you dont see this... AND DONT DO IT!"). These patterns are used specifically to enforce a particular user interface design style and do not attempt to bypass safety filters or access sensitive data.
[SAFE]: No malicious code, data exfiltration, or persistence mechanisms were detected. The external installation command (npx skills add) provided in the README is standard for the platform and references the skill's source repository.

uncodixfy