commerce-detail-page-image

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests JSON content produced by the commerce-detail-page-copy skill to create image generation prompts, which introduces an attack surface for indirect prompt injection. * Ingestion points: JSON data from commerce-detail-page-copy processed in SKILL.md. * Boundary markers: There are no explicit delimiters or instructions to the agent to ignore potential malicious content within the source JSON. * Capability inventory: The skill invokes an image generation tool and executes a local Python script with file system access. * Sanitization: No sanitization or filtering of the input text is mentioned.
  • [DYNAMIC_EXECUTION]: The skill provides an inline Python script using the Pillow library for image manipulation and composition. The agent is directed to execute this code locally to assemble the final product image.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 05:32 AM