腾讯团队评估了DeepSeek Harness的安全性，发现它能抵抗部分间接注入攻击，但仍有改进空间。
研究使用AI-Infra-Guard工具对DeepSeek Harness进行间接提示注入安全评估。实验覆盖16个间接内容通道、35个负载目标和12种攻击方法，共执行14,560次受控测试。评估采用RuleJudge和LLMJudge两种判断方法，发现文本模式下假完成攻击成功率最高达17.0%，文件模式下隐藏Unicode攻击成功率高达25.5%。研究分析了DSH工具结果处理机制，确定了应在不受信任内容和敏感操作间设置的控制措施。
Security Assessment of DeepSeek Harness with A.I.G: Evaluating Resistance to Indirect Prompt Injection
We assess indirect prompt injection in DeepSeek Harness (DSH), using AI-Infra-Guard (A.I.G) to construct tests, deliver controlled taint, execute DSH, collect traces, and judge outcomes. The study covers 14,560 controlled executions over 16 indirect-content channels, text and file carrier modes, 35 payload objectives, one unmodified baseline, and 12 attack methods. The experiment preserves DSH's agent loop, tool registry, model adapter, and session-event path; source tools and sensitive sinks are local fixtures, so attempted actions are recorded without external side effects. We evaluate each trace with a deterministic rule-based judge, \JudgeR{} (RuleJudge), and a semantic LLM-based judge, \JudgeL{} (LLMJudge). The strongest observed attack success rates are 17.0% under \JudgeL{} for fake-completion attack in text mode, 25.5% under \JudgeR{} for hidden Unicode in file mode, and 16.0% under \JudgeR{} for the skills channel in file mode. \JudgeL{} also assigns partial compliance more often than \JudgeR{} (7.3% versus 2.0%). We relate these results to DSH's treatment of tool results, additional contexts, and tool-call policy hooks, then identify controls that should sit between untrusted content and sensitive actions. Our code is available at https://github.com/Tencent/AI-Infra-Guard/tree/main/Research/deepseek-harness-security-assessment .