OpenAI Launches Daybreak for AI-Powered Vulnerability Detection and Patch Validation

OpenAI has launched Daybreak , a new cybersecurity initiative that brings together frontier artificial intelligence AI model capabilities and Codex Security to help organizations identify and patch vulnerabilities before attackers find a way in using the same issues. "Daybreak combines the...

Mini Shai-Hulud Strikes Again: TanStack + more npm Packages Compromised

Detect and mitigate malicious npm packages linked to the latest Mini Shai-Hulud supply chain campaign targeting high-value developer tooling...

Behavioral Integrity Verification for AI Agent Skills

Agent skills extend LLM agents with privileged third-party capabilities such as filesystem access, credentials, network calls, and shell execution. Existing safety work catches malicious prompts and risky runtime actions, but the skill artifact itself goes unverified. We formalize this as the...

CVE-2026-44777

jq is a command-line JSON processor. In 1.8.2rc1 and earlier, the ordinary module loader recurses without cycle detection when two otherwise valid modules include each other...

AZL-86645 CVE-2026-44777 affecting package jq for versions less than 1.7.1-6

jq is a command-line JSON processor. In 1.8.2rc1 and earlier, the ordinary module loader recurses without cycle detection when two otherwise valid modules include each other...

ALPINE-CVE-2026-44777

jq is a command-line JSON processor. In 1.8.2rc1 and earlier, the ordinary module loader recurses without cycle detection when two otherwise valid modules include each other...

CVE-2026-44777

jq is a command-line JSON processor. In 1.8.2rc1 and earlier, the ordinary module loader recurses without cycle detection when two otherwise valid modules include each other...

CVE-2026-44777 jq: stack overflow in module loading on mutual `include`

jq is a command-line JSON processor. In 1.8.2rc1 and earlier, the ordinary module loader recurses without cycle detection when two otherwise valid modules include each other...

EUVD-2026-29177

jq is a command-line JSON processor. In 1.8.2rc1 and earlier, the ordinary module loader recurses without cycle detection when two otherwise valid modules include each other...

CVE-2026-44777 jq: stack overflow in module loading on mutual `include`

jq is a command-line JSON processor. In 1.8.2rc1 and earlier, the ordinary module loader recurses without cycle detection when two otherwise valid modules include each other...

CVE-2026-44777

CVE-2026-44777 affects the jq command-line JSON processor. In versions 1.8.2rc1 and earlier, the ordinary module loader recurses without cycle detection when two otherwise valid modules include each other, leading to a stack overflow during mutual module loading. The connected documents confirm t...

CVE-2026-44777 jq: stack overflow in module loading on mutual `include`

jq is a command-line JSON processor. In 1.8.2rc1 and earlier, the ordinary module loader recurses without cycle detection when two otherwise valid modules include each other...

CVE-2026-44777

jq is a command-line JSON processor. In 1.8.2rc1 and earlier, the ordinary module loader recurses without cycle detection when two otherwise valid modules include each other...

Can You Keep a Secret? Involuntary Information Leakage in Language Model Writing

Language models are deployed in settings that require compartmentalization: system prompts should not be disclosed, chain-of-thought reasoning is hidden from users, and sensitive data passes through shared contexts. We test whether models can keep prompted information out of their writing. We giv...

Comment and Control: Hijacking Agentic Workflows Via Context-Grounded Evolution

Automation platforms such as GitHub Actions and n8n are increasingly adopting so-called agentic workflows, which integrate Large Language Model LLM agents for tasks such as code review and data synchronization. While bringing convenience for developers, this integration exposes a new risk: An...

MARGIN: Margin-Aware Regularized Geometry for Imbalanced Vulnerability Detection

Software vulnerability detection is critical for ensuring software security and reliability. Despite recent advances in deep learning, real-world vulnerability datasets suffer from two severe challenges: frequency imbalance and difficulty imbalance. We reinterpret these challenges from an embeddi...

Spring Office Hours Podcast: S5E15 - Upgrading Spring and OSS Security

Join Dan Vega and DaShaun Carter for the latest updates from the Spring Ecosystem. In this episode, Dan and DaShaun tackle two challenges every Spring developer faces: keeping applications up to date and staying ahead of security vulnerabilities in open source dependencies. They explore how AI...

Re-Triggering Safeguards within LLMs for Jailbreak Detection

This paper proposes a jailbreaking prompt detection method for large language models LLMs to defend against jailbreak attacks. Although recent LLMs are equipped with built-in safeguards, it remains possible to craft jailbreaking prompts that bypass them. We argue that such jailbreaking prompts ar...

When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven Applications

Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models LLMs that enable users to query data using conversational input rather than formal query languages such as SQL. While this paradigm significantly improves usabili...

PT-2026-39721

Name of the Vulnerable Software and Affected Versions jq versions prior to 1.8.2rc2 Description The ordinary module loader in this command-line JSON processor recurses without cycle detection when two valid modules include each other. Recommendations Update to a version later than 1.8.2rc1...