linkfox-temu-price-us
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill communicates with LinkFox's official service endpoints, including
tool-gateway.linkfox.com,api.linkfox.com, andagent-api.linkfox.com, to facilitate API requests and user account management. - [DATA_EXFILTRATION]: The skill transmits Temu access tokens and user credentials (such as verification codes during onboarding) to LinkFox's infrastructure. This is an intended and documented part of the skill's authentication and proxying mechanism.
- [COMMAND_EXECUTION]: Documentation and scripts provide instructions for users to configure environment variables and modify local shell profiles (
.bashrc,.zshrc) to store LinkFox API keys. These actions are for local configuration and require user intervention. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Temu APIs, creating a potential surface for indirect prompt injection.
- Ingestion points: Temu API responses processed by
scripts/_temu_common.pyand other business scripts. - Boundary markers: No specific delimiters or 'ignore' instructions are used when processing the JSON responses from Temu.
- Capability inventory: Includes network access for API calls and local file writing for logging results in the
linkfox/directory. - Sanitization: The skill relies on standard Python JSON parsing and serialization to handle external data structures.
Audit Metadata