linkfox-temu-ads-global
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a suite of Python scripts that the agent is instructed to execute for interacting with the LinkFox API gateway and managing local state. These scripts handle request construction, response parsing, and authentication workflows.
- [DATA_EXFILTRATION]: Store access tokens and LinkFox API keys are transmitted to tool-gateway.linkfox.com, api.linkfox.com, and agent-api.linkfox.com. These destinations are part of the vendor's established infrastructure for proxying Temu API requests and managing user accounts, representing the core functionality of the skill rather than a malicious exfiltration pattern.
- [SAFE]: The skill implements local storage of Temu access tokens in a configuration file located at ~/.linkfox/temu-access-tokens.json. This enables the agent to perform recurring tasks without requiring the user to re-authenticate for every session. Access is restricted to this specific configuration path.
- [SAFE]: While the skill processes data from external API endpoints, it does so using standard JSON serialization and structured request/response cycles. The ingestion of this data into the agent's context is performed through defined scripts that act as boundary markers, significantly reducing the risk of indirect prompt injection.
Audit Metadata