linkfox-temu-cancel-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 invocation explicitly show putting LINKFOXAGENT_API_KEY and Temu accessToken values directly into environment variables or JSON command-line arguments, which requires the agent to handle and potentially output secret values verbatim (high exfiltration risk).

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

• Third-party content exposure detected (medium risk: 0.65). At runtime the required workflow calls the Temu gateway via scripts/temu_eu_proxy.py → _temu_eu_common.py:eu_proxy_call() → _temu_common.py:call_temu_api() which ingests the gateway’s JSON response (body/temuBody) and prints/summarizes it, so any free-text fields returned by Temu (outsider-authored) can enter the agent’s LLM context through stdout.