content-research-writer
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured instructions for acting as a writing partner. No malicious patterns, obfuscation, or unauthorized data access attempts were detected.
- [COMMAND_EXECUTION]: The shell commands (mkdir, cd, touch) found in the 'How to Use' section are provided as setup instructions for the user to execute in a local terminal and are not executed by the agent automatically.
- [DATA_EXPOSURE]: The skill recommends working within a user-created 'writing' directory. No access to sensitive system paths or hardcoded credentials was found.
- [PROMPT_INJECTION]: The instructions are designed to guide the agent through a specific workflow and do not contain patterns intended to bypass safety filters or override system constraints.
- [EXTERNAL_DOWNLOADS]: No patterns for downloading or executing external scripts or packages were found.
Audit Metadata