frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a collection of design guidelines and Python-based auditing scripts. It follows best practices for a development-oriented AI agent skill.
- [COMMAND_EXECUTION]: The skill includes two Python scripts (
scripts/ux_audit.pyandscripts/accessibility_checker.py) designed to analyze local codebases for UX and accessibility compliance. These scripts perform read-only operations using regex patterns and do not execute foreign code or interact with the network. - [DATA_EXFILTRATION]: No network-capable code (e.g.,
requests,urllib,socket,curl) is present in the scripts or instructions. Data remains within the local environment specified by the user during the audit. - [INDIRECT_PROMPT_INJECTION]: While the auditing scripts ingest content from a user-provided project path, they process the data locally using static analysis (regex) and generate a summarized report. This significantly limits the attack surface for indirect prompt injection compared to skills that feed raw external content directly into the model's context.
- [OBFUSCATION]: No obfuscated content, hidden characters, or deceptive encoding techniques were found in any of the 37 files.
Audit Metadata