linkfox-temu-returns-refunds-us
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill manages Temu access tokens by storing them locally in the user's home directory (
~/.linkfox/temu-access-tokens.json) using_temu_token_store.py. This is a documented feature for session persistence across tool invocations. - [EXTERNAL_DOWNLOADS]: The skill communicates with vendor-controlled domains including
tool-gateway.linkfox.com,api.linkfox.com, andagent-api.linkfox.comto proxy API requests and manage account settings. These are verified vendor resources. - [COMMAND_EXECUTION]: The skill operates by executing local Python scripts that wrap API calls. These scripts take JSON arguments to interact with the Temu platform.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Temu API responses. While this content is placed into the agent's context, the risk is inherent to the skill's primary purpose of data retrieval. The skill implements structured output logging to the local filesystem to minimize context pollution.
- [CREDENTIALS_UNSAFE]: The skill requires a
LINKFOXAGENT_API_KEYfor gateway authentication, which is retrieved from environment variables or passed via JSON parameters. This follows standard API authentication practices.
Audit Metadata