linkfox-1688-product-detail

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Python scripts (alibaba1688_product_detail.py and onboarding.py) to interact with the LinkFox API. These scripts perform standard network operations to fetch product data and manage user authentication.
  • [EXTERNAL_DOWNLOADS]: The scripts communicate with official LinkFox API endpoints (tool-gateway.linkfox.com, api.linkfox.com, agent-api.linkfox.com) to retrieve product information and handle user logins. These are functional requirements for the skill's purpose.
  • [CREDENTIALS_SAFE]: The skill manages API keys through environment variables (LINKFOX_AGENT_API_KEY, LINKFOXAGENT_API_KEY). It does not hardcode any sensitive credentials and includes an onboarding script to help users securely set up their own keys.
  • [DATA_EXPOSURE]: The skill saves query results locally within a linkfox/ directory in the user's workspace for session persistence and caching. It explicitly avoids using shared temporary directories like /tmp to maintain data isolation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes 1688 product data including titles and descriptions which may contain HTML. The instructions include a specific rule to treat HTML as data and summarize or extract media links rather than rendering it, which serves as a mitigation against potential injection through product content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 08:34 AM
Security Audit — agent-trust-hub — linkfox-1688-product-detail