stitch-design-taste

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill focuses on providing stylistic and structural guidance for UI development. It does not contain any code for network exfiltration, credential theft, or unauthorized privilege escalation.
  • [COMMAND_EXECUTION]: The skill includes instructions for the agent to perform file system operations to maintain a history of its outputs in a local wiki directory ('llmwiki/'). These actions are consistent with documentation management and follow a predefined structure defined within the skill.
  • [PROMPT_INJECTION]: The skill uses specific constraints and 'banned' lists (e.g., prohibiting certain fonts or aesthetics like 'neon glows') to ensure a particular design quality. These are functional design parameters and do not represent attempts to bypass agent safety filters or override core system instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 09:59 AM
Security Audit — agent-trust-hub — stitch-design-taste