GitHub AI security agent

GitHub says its AI agent identified 24 vulnerabilities in Android applications, adding to growing evidence that autonomous coding assistants can take on security research tasks. The finding, reported by Help Net Security, highlights both the potential of AI-driven bug hunting and the questions it raises about verifying machine-discovered flaws. Security teams are watching closely as AI agents move into vulnerability discovery.

GitHub researchers report that an open source AI security agent they built uncovered 24 vulnerabilities in Android. The company says the tool was used to scan Android code at scale, flagging security flaws automatically. The disclosure highlights a growing trend of using AI agents to find real bugs in widely used software, and the work is being discussed as an example of AI-assisted security research.

NVIDIA has published OpenShell, a Rust-based runtime designed to let autonomous AI agents operate safely and privately. The project, hosted on GitHub, describes itself as a secure execution environment for agents, and has quickly drawn attention among developers tracking tooling for agentic AI systems.

GitHub says it discovered 24 vulnerabilities in Android using its open-source AI security agent, describing it as automated vulnerability discovery at scale on real production software. The company published details in a blog post, and the report is drawing attention as a notable demonstration of AI agents doing practical security research on widely used code.

Wiz reports that its Blue Agent, an AI-driven security tool, autonomously reconstructed a cross-platform data exfiltration attack spanning GitHub and AWS in a matter of minutes. The agent worked by correlating signals across three platforms, tracing how data could be siphoned from code repositories into cloud infrastructure. The demonstration is being circulated among security professionals as an example of how AI agents can accelerate cloud attack investigation.