The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for text refinement and does not contain any executable code, shell scripts, or binary files.
[SAFE]: The configuration in the YAML frontmatter includes disable-model-invocation: true, which restricts the agent's ability to trigger other models, reducing the potential attack surface.
[SAFE]: No evidence of prompt injection, obfuscation, or data exfiltration attempts was found. The instructions are transparent and aligned with the skill's stated purpose.

unslop