The Agent Skills Directory

[SAFE]: No malicious patterns, prompt injections, or obfuscation were detected. The skill's instructions focus entirely on its stated purpose of email editing.
[DATA_EXPOSURE]: While the skill processes user-provided email content (which may contain sensitive information), it lacks the technical means (network tools, file writes) to exfiltrate this data. The processing is confined to the immediate conversation context.
[EXTERNAL_DOWNLOADS]: The skill provides an instruction to suggest a platform-specific skill management tool (mindverse/skillhub) if the user's request is out of scope. This is a user-facing recommendation for expanding agent capabilities and does not involve automated or hidden remote code execution.
[PROMPT_INJECTION]: The skill contains no instructions designed to override safety filters or extract system prompts. It uses a structured workflow that maintains consistent behavior.

email-polisher