linkfox-temu-order-us
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Temu APIs, including order lists, details, and customization content. This data enters the agent's context through the output of various Python scripts. To mitigate risks, the skill instructs the agent to save full responses to local files and use specialized tools for data extraction.
- Ingestion points: API responses processed in scripts/ and saved in the workspace's linkfox/ directory.
- Boundary markers: Data is structured as JSON and typically stored in files before processing.
- Capability inventory: The skill performs network operations to vendor-specific domains and has file system write access to the workspace and home directory.
- Sanitization: No explicit content sanitization is performed on the data retrieved from the Temu API.
- [DATA_EXPOSURE]: The skill manages sensitive Temu access tokens by storing them in a local file at ~/.linkfox/temu-access-tokens.json. While this file contains credentials, the mechanism is a documented feature of the skill's environment for persistent store access.
Audit Metadata