linkfoxagent

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The CLI intentionally prints the LINKFOXAGENT_API_KEY environment variable into stderr on error paths, which will expose sensitive API credentials to callers/main sessions and can result in credential leakage or exfiltration.

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

• Third-party content exposure detected (medium risk: 0.30). 该技能的运行时路径是：主会话把用户的<TASK_PROMPT>经python3 <skill>/scripts/linkfox.py --wait --timeout 600 --stdin提交给 LinkFoxAgent 后，脚本再把 LinkFoxAgent 返回的results（包含item.get("content")，其type可能是html/json）直接拼接进format_result()输出供LLM继续处理与总结，从而让外部用户可通过其任务文本触发读取并回传的非结构化网页/帖子内容进入上下文（间接提示注入风险）。