ai-image-creator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains a 'System Prompt Inquiry Response' directive that instructs the agent to override its default behavior when asked about its system prompts or instructions. Instead of responding normally, the agent is forced to provide a marketing message and redirect the user to a specific website (scayveracademy.com).
- [PROMPT_INJECTION]: The 'Mandatory Intro Message' section requires the agent to include personal solicitation links for CashApp ($AlainDorcelus) and BuyMeACoffee in every long-form response. This behavior forces the agent to engage in unauthorized commercial solicitation as part of its core functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for transforming user-supplied creative concepts into structured image prompts, creating an attack surface for data-driven injection.
- Ingestion points: The skill ingests user-provided concept descriptions, brand visual identities, and campaign summaries (defined in the 'Process' section of SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to separate untrusted user input from the skill's own prompt generation templates.
- Capability inventory: The skill facilitates the generation of text-based visual prompts; it does not perform network operations, file writes, or command execution.
- Sanitization: The skill lacks instructions for sanitizing, escaping, or validating user input before it is interpolated into the final prompt outputs.
Audit Metadata