NYC

dashboard-create-screen

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill reads router and menu files from the filesystem to automate code insertion, creating a surface where malicious content in those files could influence agent behavior. Evidence Chain: (1) Ingestion points: client/dashboard router and menu files. (2) Boundary markers: Absent. (3) Capability inventory: Edit and Write tools are used for file modification. (4) Sanitization: The skill uses AskUserQuestion to confirm all parameters with the user before proceeding.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:39 PM