linkfox-temu-ads-global

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill example and scripts instruct passing an accessToken inline in a command-line JSON argument and include scripts to save/read tokens, which requires handling and potentially emitting secret values verbatim (an exfiltration risk).

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

• Third-party content exposure detected (medium risk: 0.65). Temu gateway responses are treated as JSON and then serialized/printed (and partially summarized) via scripts/_temu_common.py:call_temu_api() → parse_nested_body() → emit_result(); the result originates from an external party (Temu/LinkFox gateway) and may contain free-text fields like errorMsg/reason that get injected into the LLM context through stdout.