ecommerce-amazon-asin-keywords
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a Python script (
scripts/amazon_asin_keywords.py) to handle API communication and local caching. This is standard behavior for this type of tool. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external API, which represents a potential attack surface for indirect prompt injection if the source data were compromised.
- Ingestion points: Data is received from the NexScope API endpoint via the Python script.
- Boundary markers: No explicit delimiters or warnings are used in the data presentation to the agent.
- Capability inventory: The associated script has capabilities for network requests and file system writes.
- Sanitization: The script does not sanitize the text content of the keyword data before returning it.
Audit Metadata