design-ux-architect
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides standard web development templates for CSS, JavaScript, and Markdown. The agent persona is designed to assist developers and does not exhibit any suspicious or harmful behavior.
- [COMMAND_EXECUTION]: The skill workflow includes reading local project documentation using the
catandgrepcommands. These actions are performed on non-sensitive project files within theai/memory-bank/directory to extract context for design tasks. - [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface as it processes external data from local files. Ingestion points:
ai/memory-bank/site-setup.mdandai/memory-bank/tasks/*-tasklist.md. Boundary markers: Absent. Capability inventory:catandgrepfor file reading. Sanitization: Absent. This surface is considered safe as the agent lacks high-risk capabilities like network access or privilege escalation.
Audit Metadata