product-photo-batch-pipeline

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes product catalogue data to facilitate batch image generation, creating an attack surface where untrusted input could influence agent behavior.
  • Ingestion points: The skill iterates through a catalogue object containing product entries in the provided Python logic.
  • Boundary markers: No delimiters or explicit instructions to ignore data-embedded commands are included in the prompt construction logic.
  • Capability inventory: The skill utilizes tools for background removal, brand asset creation, image generation, and credit checking.
  • Sanitization: No explicit validation or escaping of the product metadata is implemented before it is processed or logged.
  • [EXTERNAL_DOWNLOADS]: The skill instructions include adding an MCP server from a domain associated with the skill author.
  • Evidence: https://mcp.apimage.org/mcp
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 12:36 AM