linkfox-amazon-product-detail
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted content (product titles, descriptions, and reviews) from Amazon marketplaces. Malicious actors could place instructions within Amazon listings to influence the agent's behavior.
- Ingestion points:
scripts/amazon_product_detail.pyfetches external data via the LinkFox API gateway. - Boundary markers: There are no explicit instructions or delimiters defined in the prompt to help the agent distinguish between its operational instructions and the untrusted data being analyzed.
- Capability inventory: The skill utilizes file system writes to store JSON responses and performs network operations across multiple scripts.
- Sanitization: The implementation does not include sanitization or filtering of the retrieved Amazon product data.
- [COMMAND_EXECUTION]: The skill uses a Python script (
scripts/amazon_product_detail.py) to interface with the LinkFox API. The script correctly parses parameters as JSON, which prevents traditional shell command injection. - [EXTERNAL_DOWNLOADS]: The skill performs network requests to subdomains of
linkfox.com(e.g.,tool-gateway.linkfox.com,api.linkfox.com,agent-api.linkfox.com). These are the official domains of the skill's vendor,linkfox-ai, and are used for data retrieval, authentication, and billing services.
Audit Metadata