linkfox-amazon-product-detail
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local Python script (
scripts/amazon_product_detail.py) to handle API requests and data processing. - [DATA_EXFILTRATION]: Product identifiers (ASINs) and user feedback are transmitted to official vendor-controlled endpoints (
tool-gateway.linkfox.comandskill-api.linkfox.com). - [CREDENTIALS_UNSAFE]: No hardcoded secrets were detected; the skill provides clear instructions for managing API keys through the
LINKFOXAGENT_API_KEYenvironment variable. - [PROMPT_INJECTION]: The skill processes untrusted external content (Amazon product descriptions and reviews) which serves as a surface for indirect prompt injection. Ingestion points: API responses from
tool-gateway.linkfox.com. Boundary markers: Absent. Capability inventory: API interaction and data rendering. Sanitization: Not explicitly implemented in the provided scripts.
Audit Metadata