amazon-review-analyzer

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The installation process fetches the skill package from the author's official GitHub repository (nexscope-ai/eCommerce-Skills).
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.
  • Ingestion points: Processes product reviews from multiple external platforms including Amazon, Shopify, Walmart, and TikTok Shop.
  • Boundary markers: The instructions do not define delimiters or specific markers to separate untrusted review content from agent instructions.
  • Capability inventory: The skill utilizes the agent's natural language processing and reasoning capabilities to categorize complaints and suggest product improvements.
  • Sanitization: No explicit sanitization, filtering, or instruction-disregard logic is present to handle malicious content embedded within user reviews.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 07:29 AM