agent-ux
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to provide structured guidelines and templates for improving AI agent interactions with user interfaces. No evidence of malicious intent or safety bypasses was found.
- [COMMAND_EXECUTION]: The skill includes a shell script (
evals/run-static-checks.sh) intended for development-time validation. This script performs static analysis on the skill's structure using local scripts from the parent repository and does not execute untrusted remote code or perform unauthorized network operations. - [PROMPT_INJECTION]: Instructions focus on routing and auditing workflows. There are no attempts to override system prompts or bypass safety guardrails.
- [DATA_EXFILTRATION]: No sensitive file paths, hardcoded credentials, or unauthorized network operations were detected. The skill specifically states that bare invocation involves no file inspection or network calls.
Audit Metadata