product-feed-qa-ecommerce

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze potentially untrusted external data sources, which could contain malicious instructions.
  • Ingestion points: The workflow requires inputting product feed CSV samples, Merchant Center diagnostic exports, and product page URLs.
  • Boundary markers: There are no instructions for the agent to use specific delimiters or protective boundary markers when processing these external data points.
  • Capability inventory: While the skill itself is markdown-based, it guides the agent to perform analysis on files and URLs, which typically involves file-reading and web-browsing capabilities.
  • Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the incoming data before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:24 AM