The Agent Skills Directory

[SAFE]: No security vulnerabilities were detected in the analyzed files. The skill consists exclusively of natural language instructions for the AI agent to follow when rewriting user-provided text for better clarity and tone.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process untrusted user-provided prose, which is an inherent surface for indirect prompt injection, it lacks any dangerous capabilities (such as tool use, file writing, or network access) that could be exploited. The instructions include a specific step to 'Identify the output boundary' and separate conversational prose from structured content, which serves as a security best practice for handling untrusted data.

unslop