linkfox-temu-manage-product-us
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to proxy requests to Temu APIs through the author's gateway at
tool-gateway.linkfox.com. All network activity targets verified vendor and service domains. - [SAFE]: Temu access tokens are managed through a local store in the user's home directory (
~/.linkfox/temu-access-tokens.json). This is a standard and acceptable method for managing credentials in CLI-based agent skills. - [SAFE]: The Python scripts are clear and use standard libraries for networking and file system interaction. There is no evidence of obfuscation, multi-layer encoding, or unauthorized command execution.
- [SAFE]: Indirect Prompt Injection Surface:
- Ingestion points: External product data and status information fetched from Temu APIs in scripts such as
us_manage_list_query.py. - Boundary markers: Responses are handled as JSON objects; no specific prompt delimiters are used to isolate untrusted data.
- Capability inventory: The skill can write results to the local filesystem and perform network requests to LinkFox gateways.
- Sanitization: Content retrieved from Temu is saved and displayed without specific sanitization against embedded instructions. However, the risk is considered safe due to the trusted nature of the data source.
Audit Metadata