NYC

frontend-architect

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • NO_CODE (SAFE): The skill is composed of markdown instructions and does not include any scripts or executable files.
  • PROMPT_INJECTION (SAFE): There are no instructions intended to subvert AI safety protocols or extract system prompts.
  • DATA_EXFILTRATION (SAFE): No logic exists for making network requests or accessing sensitive local data.
  • INDIRECT_PROMPT_INJECTION (SAFE): The agent is instructed to analyze project files, which is a potential ingestion point, but the skill has no dangerous capabilities that could be triggered by malicious file content. [Ingestion points: package.json, build configs; Boundary markers: None; Capability inventory: None; Sanitization: None]
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:38 PM