social-commerce-product-images
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to configure a Model Context Protocol (MCP) server using the vendor's official domain:
https://mcp.apimage.org/mcp. - [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external data during image generation.
- Ingestion points: External image references (
PRODUCT_REFS) and user-supplied product descriptions are interpolated into image generation prompts inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential injections within the product references.
- Capability inventory: The skill utilizes a
generate_imagetool to process these inputs and produce visual outputs. - Sanitization: No explicit sanitization or validation logic is provided for the input metadata or image references.
Audit Metadata