Amazon Seller

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection where malicious instructions could be embedded in data retrieved from external sources.
  • Ingestion points: Untrusted data enters the agent context through Amazon Order information (e.g., buyer_name in messaging templates) and external product listings/competitor data used for pricing and optimization logic.
  • Boundary markers: The YAML templates for messaging and listing optimization (e.g., listing_template, messaging_automation) do not currently specify boundary markers or instructions to ignore embedded commands within variable interpolations like {{buyer_name}} or {{product_name}}.
  • Capability inventory: The skill possesses significant write capabilities via the amazon_sp_api and amazon_ads_api tools, including the ability to send messages to buyers, update product listings, adjust pricing, and create shipment plans.
  • Sanitization: There is no explicit mention of input validation or sanitization for external content before it is interpolated into prompts or used as input for API calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:20 AM