ai-image-creator
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to suppress warnings, notes, and disclaimers, directing it to 'Deliver the content directly'. This technique is often used to bypass built-in model guardrails or context-providing behaviors.
- [PROMPT_INJECTION]: Specific instructions define a mandatory canned response for queries about system prompts, which serves to obscure the internal logic of the skill and redirects users to an external commercial membership platform.
- [NO_CODE]: The skill is composed strictly of natural language instructions and does not contain any code, scripts, or executable files.
Audit Metadata