chinese-copywriting
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use local shell utilities to generate differences between original and corrected text.
- Evidence: Located in the 'Step 2' section of SKILL.md, using
catanddiff -uon temporary files in/tmp/. - Security Context: The use of quoted heredocs (
<<'EOF') prevents variable expansion or command execution within the user text, mitigating potential injection risks during comparison.
Audit Metadata