imagegen-frontend-mobile
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is comprised of markdown instructions defining design aesthetics, platform modes, and quality checks for image generation. It does not interact with the file system, network, or external APIs.
- [NO_CODE]: The instructions include multiple explicit directives ('Do not switch into coding mode', 'It does not write code') that prevent the agent from generating executable scripts or frontend implementation code.
- [PROMPT_INJECTION]: The use of 'CORE DIRECTIVE' and 'MANDATORY' rules is limited to defining the creative output style and persona. There are no attempts to bypass safety guardrails, extract system prompts, or ignore established AI constraints.
- [DATA_EXFILTRATION]: There is no evidence of commands that access sensitive files or perform network operations to exfiltrate data.
- [OBFUSCATION]: The content is clear text with no hidden characters, encoded strings, or homoglyph attacks.
Audit Metadata