linkfox-temu-tax-eu

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill's examples and usage require providing Temu access tokens (and show them embedded inline in CLI JSON) which instructs the agent or user to place secret values verbatim into commands/arguments, creating an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.65). Required runtime path calls the Temu gateway (scripts/_temu_common.py:95-121 → call_temu_api reads response.read() and parses JSON), and that upstream response is then emitted/summarized by emit_result (scripts/_temu_common.py:308-332), so any free-text fields returned by the outsider (Temu/LinkFox gateway) can enter the agent’s LLM context via stdout.