The Agent Skills Directory

[SAFE]: No security issues were detected. The skill is designed as a meta-instruction for text-to-text transformations.
[PROMPT_INJECTION]: The skill defines a structured prompt template using markers like ## INPUT and ## INSTRUCTION to separate untrusted user data from instructions. This structural separation is a security best practice to mitigate prompt injection.
[DATA_EXFILTRATION]: The skill does not perform any network operations or access sensitive file paths. Its output contract is strictly limited to returning plain text or JSON to the calling agent.
[COMMAND_EXECUTION]: The skill does not execute shell commands or use any dangerous tools. It delegates all 'mechanics' (like regex or parsing) to the external calling code rather than performing them within the agent context.

textprocessing