The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown files (SKILL.md, CHANGELOG.md, and several files in the references/ directory) that provide instructions and examples for prose editing. No scripts, binaries, or automated tasks are included.
[SAFE]: No network operations, external downloads, or remote code execution patterns were detected. The skill operates entirely within the text-processing capabilities of the agent.
[SAFE]: There are no references to sensitive file paths (e.g., credentials, SSH keys, or environment variables) or hardcoded secrets.
[INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to process and rewrite user-provided text. While this involves ingesting untrusted data, the skill lacks any executable tools or network capabilities that could be exploited by malicious content within the prose being edited. The risk is negligible.

stop-slop