seo-image-generator
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's operations are instructional and focused on generating prompts from templates. It does not contain any executable code, shell commands, or unauthorized network operations.
- [PROMPT_INJECTION]: The skill ingests user-provided data such as brand names and website URLs and interpolates them into prompts for an image generator. While this creates a potential surface for indirect prompt injection if a user provides text designed to manipulate the image model, the functionality is necessary for the skill's primary purpose and does not affect the safety of the agent itself.
- Ingestion points: User-provided Brand Name, Website URL, and Visual Direction collected in Step 3 and Step 1.
- Boundary markers: Not utilized in prompt templates found in references/prompt-templates.md.
- Capability inventory: Interacts with external image generation services via the agent's existing capabilities.
- Sanitization: No explicit sanitization of user-provided strings is observed prior to prompt interpolation.
Audit Metadata