ios-app-assets

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for generating images using a local script (nanobanana.ts) and processing them with ImageMagick. No malicious patterns such as obfuscation, data exfiltration, or unauthorized command execution were detected.
  • [SAFE]: Operations are restricted to local environments, and no external dependencies or remote code downloads are utilized.
  • [SAFE]: Indirect Prompt Injection Surface: The skill interpolates user-provided descriptions into shell commands. This represents a potential surface for injection if inputs are not properly sanitized by the underlying agent platform, though the provided templates use quoted strings to mitigate common shell injection issues.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 07:18 PM