The Agent Skills Directory

[SAFE]: The skill consists of markdown instructions and configuration files for technical text refinement. It does not contain any executable scripts, command line invocations, network operations, or sensitive file system access.
[INDIRECT_PROMPT_INJECTION]: The skill serves as a processor for untrusted technical prose (such as Pull Request bodies, issue descriptions, and documentation). While this represents a data ingestion point, the skill lacks dangerous capabilities like shell execution or network exfiltration, and explicitly instructs the agent to preserve code blocks and literals, which helps maintain boundaries against malicious data.

write-ste