TechPrufer
Get started
Datadog
Datadog logoDatadog · Feature trail

Malicious Code Detection

3 posts · Oct 2025 – Jun 2026

What this trail covers

Datadog's BewAIre system has evolved from detecting malicious code in pull requests to scanning entire dependency packages and upstream package registries. This expansion leverages a two-stage evaluation pipeline: a fast, inexpensive filter phase using a previous-generation or high-speed LLM, followed by a more thorough agentic investigation phase for flagged changes. The investigation phase utilizes tools to gather additional context, such as GitHub API calls for commit history, contributor analysis, and code execution sandboxing. The system is now integrated into the CI/CD pipeline to review all pull requests in real-time, classifying them as benign or malicious with a low false positive rate. This evolution aims to address the growing attack surface and reviewer fatigue associated with AI-assisted development.

All Datadog trails
  1. Scaling malicious code detection from pull requests to the software supply chain | DatadogThis post details the expansion of Datadog's BewAIre system from detecting malicious code in pull requests to scanning entire dependency packages and upstream package registries. The core technical contribution is the implementation of a two-stage evaluation pipeline: a fast, inexpensive filter phase using a previous-generation or high-speed LLM, followed by a more thorough agentic investigation phase for flagged changes. The investigation phase utilizes tools to gather additional context, such as GitHub API calls for commit history, contributor analysis, and dependency validation against external resources. The post highlights engineering trade-offs in scaling malicious code detection across ecosystems while maintaining high accuracy and operational efficiency, including a preprocessing pipeline for domain typosquatting checks.
  2. When an AI agent came knocking: Catching malicious contributions in Datadog’s open source repos | DatadogThis post details how Datadog's BewAIre system detected and defended against the 'hackerbot-claw' AI agent, which attempted to exploit CI-related vulnerabilities in open-source repositories. It highlights the evolution of defensive strategies to counter AI-driven attacks, including prompt injection detection against LLM-powered actions and hardening CI/CD workflows against indirect poisoned pipeline execution and insecure variable interpolation. The post also emphasizes the importance of integrating security findings into SIEM and incident response processes, and outlines ongoing efforts in secure SDLC practices like dynamic credential generation and enforcing CI security best practices.
  3. Detecting malicious pull requests at scale with LLMs | DatadogThis post details the evolution of Datadog's malicious code detection system, BewAIre, which now reviews all pull requests in real-time using LLMs. It describes the challenges of increased PR volume due to AI-assisted development, the limitations of traditional static analysis tools, and the system's architecture for ingestion, preprocessing, and inference. Key technical details include the use of prompt engineering and data tuning for accuracy, strategies for working around LLM context window limitations, and continuous testing against real-world exploits. The system achieved >99.3% accuracy with a 0.03% false positive rate on a curated dataset and demonstrated 100% detection of known malicious package compromises. The post also highlights the importance of building a custom dataset of malicious and benign PRs, as no ready-made repository exists.