linkfox-temu-cancel-order-eu
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous Python scripts that act as command-line interfaces for specific Temu API endpoints. These scripts process user-provided JSON arguments to perform e-commerce operations.
- [EXTERNAL_DOWNLOADS]: The skill initiates network communication with vendor-controlled domains, including
linkfox.com,linkfox-ai.com, andtemu.com. These connections are used for API proxying, user authentication, and retrieving configuration data. - [CREDENTIALS_UNSAFE]: To support persistent authentication, the skill includes logic to save Temu access tokens in a local configuration file (
~/.linkfox/temu-access-tokens.json). It also utilizes theLINKFOXAGENT_API_KEYenvironment variable for gateway authentication, following established vendor security patterns. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Temu API responses. It mitigates potential prompt injection risks and context limitations by summarizing large JSON responses before they are returned to the agent's main context.
Audit Metadata