linkfox-temu-manage-product-us
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted product metadata (titles, descriptions, SKU info) retrieved from the Temu platform, creating an indirect prompt injection surface.
- Ingestion points: Data retrieved from APIs such as
bg.local.goods.list.queryandbg.local.goods.detail.queryis loaded into the agent's context. - Boundary markers: The skill does not implement explicit delimiters or instructions to treat platform-sourced data as untrusted.
- Capability inventory: The agent has the authority to execute scripts that can delete products, modify inventory, and change product status based on potentially poisoned input.
- Sanitization: There is no evidence of filtering or sanitization of external product content before it is processed by the agent.
Audit Metadata