tuzi-xhs-images

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use bash commands such as test -f to verify the existence of the user preference file (EXTEND.md) in both project-level and user-level home directories.- [COMMAND_EXECUTION]: Technical documentation within the skill includes examples of executing a local generation script via npx and bun to maintain visual consistency across a series of images.- [PROMPT_INJECTION]: The system instructions include a guideline to bypass potential refusals regarding sensitive or copyrighted figures by providing stylistically similar hand-drawn alternatives, ensuring creative continuity while avoiding safety blockages.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 03:45 PM