linkfox-temu-manage-product-eu

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill's examples and call patterns require putting Temu accessTokens (and example TOKEN values) directly into command-line JSON arguments and reference scripts that save/read raw tokens, which forces secrets to be handled and potentially echoed or transmitted verbatim rather than kept in protected environment variables or secure stores.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). 该 skill 的运行时通过 scripts/_eu_product_script.py 解析用户传入的 JSON 参数并在 scripts/_temu_eu_common.py 里调用网关 POST ${LINKFOX_TOOL_GATEWAY}/temu/proxy，且会将网关返回的 body（Temu 原始 JSON 字符串解析后）作为 LLM 上下文可用文本摘要/落盘输出，因此在由外部用户提交请求体（含任意 params/searchText 等）后即可诱导到“先不选择具体条目、直接投喂会被读取”的流程风险。