ios-onboarding-advisor

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill contains no executable code, shell commands, or network requests. It is entirely composed of natural language instructions and design principles.
  • [NO_CODE]: This skill functions as a 'lens' or persona for an AI agent, providing domain-specific knowledge without the use of scripts, binaries, or external dependencies.
  • [DATA_EXPOSURE]: While the skill is designed to analyze screenshots or descriptions of app flows provided by the user, it lacks any capability to exfiltrate this data or access sensitive system files.
  • [PROMPT_INJECTION]: No evidence of prompt injection or behavior override instructions were found. The 'Portability note' describes how the lens should be applied logically and does not contain malicious override patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 01:51 AM
Security Audit — agent-trust-hub — ios-onboarding-advisor