linkfox-temu-price-global

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple Python scripts to facilitate API communication and local state management, such as token storage and retrieval.
  • [EXTERNAL_DOWNLOADS]: Performs network operations to interact with vendor services at linkfox.com and Temu's official OpenAPI gateway. This includes a user onboarding process that sends registration data to the vendor's authentication server.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection (Category 8) by ingesting data from external API responses and incorporating it into the agent's context.
  • Ingestion points: API responses received in scripts/temu_proxy.py and price-specific query scripts.
  • Boundary markers: API outputs are printed to context without specific delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill has the ability to execute shell commands and write files to the workspace.
  • Sanitization: JSON responses are formatted or summarized but not sanitized to prevent potential instruction execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:03 AM
Security Audit — agent-trust-hub — linkfox-temu-price-global