NYC

frontend-design

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOW
Full Analysis
  • Prompt Injection (SAFE): No malicious instructions or safety filter bypasses were detected. The use of 'IMPORTANT' and 'CRITICAL' markers is consistent with benign stylistic guidance for the AI.
  • Data Exposure & Exfiltration (SAFE): The skill does not access sensitive local files or perform unauthorized network requests.
  • External Downloads (SAFE): Contains a reference to an official Anthropic cookbook on GitHub, which is a verified trusted source. No runtime script downloads or executions occur.
  • Obfuscation (SAFE): No encoded strings, zero-width characters, or hidden payloads were found within the documentation or skill files.
  • Indirect Prompt Injection (SAFE): While the skill processes user design requirements, it does so to generate UI code for display purposes and lacks capabilities for file modification, command execution, or network exfiltration.
  • Dynamic Execution (SAFE): No patterns of runtime compilation, unsafe deserialization, or code injection were identified.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 10:56 PM