The Agent Skills Directory

[SAFE]: No malicious patterns detected. The skill instructions are strictly focused on UX writing and content auditing tasks. \n- [DATA_EXFILTRATION]: The skill does not access sensitive system paths (e.g., .ssh, .aws, or environment variables) or attempt to exfiltrate data. All file operations are confined to standard documentation and workspace paths such as .sage/docs/ and .sage/work/. \n- [REMOTE_CODE_EXECUTION]: No mechanisms for downloading or executing remote code were found. The skill does not utilize package managers or remote scripts. \n- [COMMAND_EXECUTION]: The skill does not contain instructions to execute shell commands, system scripts, or other potentially dangerous tools. \n- [PROMPT_INJECTION]: No patterns associated with prompt injection, such as bypassing safety filters or overriding system instructions, were identified.

ux-writing