linkfox-temu-order-eu

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's examples and CLI usage explicitly require embedding API tokens (e.g., accessToken, LINKFOXAGENT_API_KEY) directly in command-line JSON arguments and show exporting/printing keys, which requires the LLM to handle/output secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.75). Runtime path: the skill calls Temu’s gateway (scripts/_temu_common.py:96-121 → scripts/_temu_eu_common.py:65-68 → scripts/_temu_eu_common.py:89-91), parses the returned JSON (scripts/_temu_common.py:152-160), and then prints/summarizes it (scripts/_temu_common.py:309-333), so any free-text fields in the outsider-authored Temu response (e.g., errorMsg, warning, fulfillmentWarning, customizedText) can enter the LLM context via the tool output.