linkfox-temu-returns-refunds-eu
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a modular script architecture (e.g.,
temu_eu_proxy.py,eu_returns_refunds_aftersales_aftersales_list_get.py) to interface with external APIs. These scripts are invoked with JSON-formatted arguments to handle business logic.\n- [DATA_EXFILTRATION]: The skill reads authentication tokens from a local store (~/.linkfox/temu-access-tokens.json) and environment variables (LINKFOXAGENT_API_KEY), sending this information along with business parameters to vendor-managed gateway endpoints atlinkfox.com. This facilitates secure proxying of requests to Temu's infrastructure.\n- [INDIRECT_PROMPT_INJECTION]: Data retrieved from external API endpoints is ingested and processed by the agent. The skill implements a strategy to save full JSON responses to the local file system while presenting only summaries to the agent for large data sets, which serves as a boundary against potential prompt injection within the external data.
Audit Metadata