linkfox-temu-promotion-us

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's examples and CLI usage show API tokens exported and passed verbatim in command-line JSON (e.g., export LINKFOXAGENT_API_KEY and python ... '{"accessToken":"TOKEN",...}'), which requires the LLM to include secret values verbatim in generated commands/requests, creating an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). Runtime path scripts/*us_promotion_*.py → _us_promotion_script.run_cli → us_proxy_call() → call_temu_api(PROXY_URL, body) sends user-provided params (including free-form strings like traceCode, activityName-carrying fields returned by Temu) and then parses and emits the upstream JSON body/result into the agent context via emit_result() (summaries or full JSON), so outsider-authored text from user-controlled request/response channels is LLM-ingested.