ecommerce-amazon-reviews-list
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of Amazon product reviews which are considered untrusted sources. 1. Ingestion points: Review data is fetched from the NexScope API in the scripts/amazon_reviews.py script. 2. Boundary markers: The skill instructions do not explicitly provide delimiters to separate review text from agent instructions. 3. Capability inventory: The skill performs network requests to the vendor API and writes JSON data to a dedicated local directory within the project. 4. Sanitization: No content filtering or sanitization is performed on the review text prior to analysis.
- [SAFE]: The skill's behavior is consistent with its stated purpose of product research. It uses standard environment variables for authentication and implements robust local caching and output management without accessing sensitive system files or executing unauthorized commands.
Audit Metadata