linkfox-temu-cancel-order-global

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly requires supplying API credentials (LINKFOXAGENT_API_KEY and Temu accessToken/storeKey) in environment variables and JSON/CLI arguments, which would force the LLM/agent to handle and potentially emit secret values verbatim in commands or requests.

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

• Third-party content exposure detected (high risk: 0.85). Required workflow calls Temu via the LinkFox gateway (scripts/_temu_common.py → call_temu_api() → response.read() → json.loads()), then emit_result() prints/summarizes the gateway’s returned JSON (which is outsider-controlled data from Temu) into the agent’s LLM context via stdout.