The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions providing stylistic guidelines for rewriting text. No malicious patterns, command executions, or hidden instructions were found across the files.
[NO_CODE]: There are no executable scripts, dependencies, or binary files included in this skill. The agents/openai.yaml file is a standard configuration for agent identity and invocation policy.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process arbitrary input text for rewriting. While this is an indirect injection surface, the skill does not grant the agent access to sensitive tools, file systems, or network resources, rendering the risk negligible. The instructions specifically guide the AI to treat the input as text to be edited, rather than instructions to be followed.

unslop