image-generation
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines operational logic for selecting image generation tools based on user requirements. All identified external resources (fal.ai, hyperfx-ai.ai) are well-known services or vendor-owned infrastructure.- [INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection by processing external website content to generate image prompts.
- Ingestion points: Third-party website data is ingested via "firecrawl_extract_branding" and "firecrawl_scrape_url" as described in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or boundary markers to separate extracted external content from the agent's internal prompt instructions.
- Capability inventory: The skill utilizes image generation tools including "openai_image_generation", "nano_banana_image_generation", and "seedream_image_generation".
- Sanitization: There is no evidence of sanitization or filtering of the extracted website data (colors, fonts, tone) before it is interpolated into generation prompts.
Audit Metadata