ui-design-ethos

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were detected in the skill instructions or reference documents. The skill follows established design guidelines from well-known technology companies.
  • [DATA_EXPOSURE]: The skill restricts its tool usage to local file reading via the allowed-tools configuration. It does not attempt to access sensitive system files (e.g., .ssh, .env, .aws) or hardcode credentials.
  • [COMMAND_EXECUTION]: There are no instances of arbitrary command execution or shell script invocation. The skill relies on structured protocols for text analysis and generation.
  • [INDIRECT_PROMPT_INJECTION]: The skill's /ui-audit mode processes user-provided content such as component code or URL descriptions. This represents a potential surface for indirect prompt injection. However, since the skill is restricted to read-only filesystem tools and lacks the ability to execute code or make unauthorized network requests, the risk of exploitation is minimal and inherent to the skill's primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 03:39 PM