The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language documentation and workflow guidelines. It does not include any scripts, command execution, or file system access.- [INDIRECT_PROMPT_INJECTION]: The workflow involves reading external artifacts such as user complaints and QA evidence. While these sources represent an ingestion point for untrusted data, the skill is purely instructional and lacks dangerous capabilities like automated execution, file writes, or network exfiltration that would make such an injection exploitable.

re0-work