CROWDSTRIKE RESEARCH: SECURITY FLAWS IN DEEPSEEK-GENERATED CODE LINKED TO POLITICAL TRIGGERS

CrowdStrike Counter Adversary Operations identifies innocuous trigger words that lead DeepSeek to produce more vulnerable code.

- 

In January 2025, China-based AI startup DeepSeek released DeepSeek-R1, a high-quality large language model (LLM) that allegedly cost much less to develop and operate than Western competitors' alternatives.

CrowdStrike Counter Adversary Operations conducted independent tests on DeepSeek-R1 and confirmed that in many cases, it could provide coding output of quality comparable to other market-leading LLMs of the time. However, we found that when DeepSeek-R1 receives prompts containing topics the Chinese Communist Party (CCP) likely considers politically sensitive, the likelihood of it producing code with severe security vulnerabilities increases by up to 50%.

This research reveals a new, subtle vulnerability surface for AI coding assistants. Given that up to 90% of developers already used thes tools in 2025,1 often with access to high-value source code, any systemic security issue in AI coding assistants is both high-impact and high-prevalence.

CrowdStrike's research contrasts with previous public research, which largely focused on either traditional jailbreaks, like trying to get DeepSeek to produce recipes for illegal substances or endorse criminal activities, or on prompting it with overtly political statements or questions to provoke it to respond with a pro-CCP bias.2

Since the initial release of DeepSeek-R1 in January 2025, a plethora of other LLMs by Chinese companies has been released (several other DeepSeek LLMs, the collection of Alibabas latest Qwen3 models, and MoonshotAI's Kimi K2, to name a few). While our research specifically focuses on the biases intrinsic to DeepSeek-R1, these kinds of biases could affect any LLM, especially those suspected to have been trained to adhere to certain ideological values.

We hope by publishing our findings we can help spark a new research direction into the effects that political or societal biases in LLMs can have on writing code and other tasks.

Disambiguation