linkfox-maidalv-product-tro-detection

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Python scripts to interact with the LinkFox API and manage local image uploads. These scripts (maidalv_check_api_flash.py, upload_image.py, and onboarding.py) are executed via shell commands. The operations include sending HTTP requests to vendor-owned domains and handling local file reading for uploads, which are consistent with the skill's stated purpose.
  • [EXTERNAL_DOWNLOADS]: The skill downloads and manages images for IP risk detection. Specifically, upload_image.py facilitates uploading local images to a presigned URL on tool-gateway.linkfox.com (a vendor domain) to obtain a public URL for the main detection API. This is a standard functional requirement for processing local files in a cloud-based detection environment.
  • [DATA_EXPOSURE]: The skill handles product images and metadata which are sent to the LinkFox API for analysis. It also manages user credentials (API keys) stored in environment variables (LINKFOX_AGENT_API_KEY). The onboarding.py script assists users in obtaining and setting these keys securely via a login process. There is no evidence of these credentials being exfiltrated to non-vendor domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:02 AM
Security Audit — agent-trust-hub — linkfox-maidalv-product-tro-detection