EUVD-2024-37173

Malicious code in bioql PyPI...

EUVD-2025-18114

Malicious code in bioql PyPI...

EUVD-2025-24366

Malicious code in bioql PyPI...

Empowering defenders in the era of agentic AI with Microsoft Sentinel

Microsoft unveils a new wave of security innovation—delivering an agentic platform to protect organizations at scale We are living through a turning point in how organizations work and defend themselves. Across industries, “Frontier Firms” are emerging; these are businesses where humans and AI...

Microsoft Expands Sentinel Into Agentic Security Platform With Unified Data Lake

Microsoft on Tuesday unveiled the expansion of its Sentinel Security Incidents and Event Management solution SIEM as a unified agentic platform with the general availability of the Sentinel data lake. In addition, the tech giant said it's also releasing a public preview of Sentinel Graph and...

Kicking off Cybersecurity Awareness Month 2025: Researcher spotlights and enhanced incentives

October marks Cybersecurity Awareness Month, a time when the developer community reflect on the importance of security in the evolving digital landscape. At GitHub, we understand that protecting the global software ecosystem relies on the commitment, skill, and ingenuity of the security research...

GitHub's Copilot Code Review: Can AI Spot Security Flaws Before You Commit?

As software development practices increasingly adopt AI-powered tools, ensuring that such tools can support secure coding has become critical. This study evaluates the effectiveness of GitHub Copilot's recently introduced code review feature in detecting security vulnerabilities. Using a curated...

EchoLeak: the First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System

Large language model LLM assistants are increasingly integrated into enterprise workflows, raising new security concerns as they bridge internal and external data sources. This paper presents an in-depth case study of EchoLeak CVE-2025-32711, a zero-click prompt injection vulnerability in Microso...

Obsidian GitHub Copilot Plugin stores sensitive information in cleartext

Overview Obsidian GitHub Copilot Plugin provided by Pierre-Adrien Vasseur is vulnerable to the following vulnerability. Cleartext storage of sensitive information CWE-312 - CVE-2025-58401 Rui Nakajima reported this vulnerability to IPA. JPCERT/CC coordinated with the developer under Information...

CVE-2025-58401

Obsidian GitHub Copilot Plugin versions prior to 1.1.7 store Github API token in cleartext form. As a result, an attacker may perform unauthorized operations on the linked Github account...

CVE-2025-58401

Obsidian GitHub Copilot Plugin versions prior to 1.1.7 store Github API token in cleartext form. As a result, an attacker may perform unauthorized operations on the linked Github account...

CVE-2025-58401

Obsidian GitHub Copilot Plugin versions prior to 1.1.7 store Github API token in cleartext form. As a result, an attacker may perform unauthorized operations on the linked Github account...

PT-2025-36109

Name of the Vulnerable Software and Affected Versions: Obsidian GitHub Copilot Plugin versions prior to 1.1.7 Description: The Obsidian GitHub Copilot Plugin stores Github API tokens in cleartext form. This allows an attacker to perform unauthorized operations on the linked Github account...

Obsidian GitHub Copilot Plugin 安全漏洞

Obsidian GitHub Copilot Plugin is a Github Copilot plugin by the individual developer Pierre-Adrien Vasseur. A security vulnerability exists in versions of Obsidian GitHub Copilot Plugin prior to 1.1.7, which stems from storing Github API tokens in clear-text form, which could lead to unauthorize...

CVE-2025-55242 Xbox Certification Bug Copilot Djando Information Disclosure Vulnerability

...

CVE-2025-55242

CVE-2025-55242 affects Xbox Gaming Services/Xbox (Xbox Certification Bug Copilot Djando Information Disclosure Vulnerability). Description: exposure of sensitive information to an unauthorized actor over a network. Affected component is related to Xbox Gaming Services; root cause described as an ...

CVE-2025-55242 Xbox Certification Bug Copilot Djando Information Disclosure Vulnerability

...

Adversarial Bug Reports As a Security Risk in Language Model-Based Automated Program Repair

Large Language Model LLM - based Automated Program Repair APR systems are increasingly integrated into modern software development workflows, offering automated patches in response to natural language bug reports. However, this reliance on untrusted user input introduces a novel and underexplored...

Malicious code in @xd37hxassent/copilot-poc-jira (npm)

The package communicates with a domain associated with malicious activity. --- -= Per source details. Do not edit below this line.=-...

Securing and governing the rise of autonomous agents​​

In this blog, you will hear directly from Corporate Vice President and Deputy Chief Information Security Officer CISO for Identity, Igor Sakhnov, about how to secure and govern autonomous agents. This blog is part of a new ongoing series where our Deputy CISOs share their thoughts on what is most...