ai-security 56
- Agents didn’t break code review, they exposed it
- Probably Not Exploitable
- Bring a tent, I've got the coffee: Lessons from it-sa
- Abliterated Models in Appsec Pentesting
- Discovering a Backdoor and Flaws in More Encrypted USB Drives
- There's only so much code: the rise in vulnerability numbers
- Jev as a judge: How counterfeit policy steers Jev
- Sonar joins OpenAI Daybreak Cyber Partner Program, deepening collaboration on agentic security
- OpenAI GPT-6.1 Sol: An evaluation
- One breach, please, and make no mistakes
- The model isn't cooperating
- AWS Security Digest #281 - Package Deal
- OpenAI GPT-6 Sol: An evaluation
- Introducing CAIRN: Frontier tracking for AI-integrated malware
- Should you care about an “AI slowdown?”
- 1Password's AI patching benchmark is misleading
- Your AI agent doesn't know your codebase's context or constraints, and that's costing you
- The Role of Agentic AI in Cybersecurity
- Don't Let Abliteration Abliterate Your Bug Hunting: Discovering Verdict Bias in Uncensored Models
- AWS Security Digest #276 - Uncontained
- VMs won't contain cyber-capable agents
- The safety penalty: Reclaiming operational sovereignty in the age of AI
- From signals to systemic risk: Building Risk AI
- Everything is about to “go dark”
- The Good, the Bad and the Ugly in Cybersecurity – Week 32
- Can AI do novel security research? Meet the HTTP Terminator
- The Good, the Bad and the Ugly in Cybersecurity – Week 31
- From capable AI models to trusted security testing
- Slop Cleanup Duty
- Prompt Engineering for Security Agents - A Measurable Approach with GEPA
- The risk hiding behind exposed MCP servers
- How we use /goal to find bugs in Patch the Planet
- Oh My Rogue Agent
- Introducing SonarQube Server 2026.4
- Detection Engineering in the Era of Semantic Malware
- GhostApproval: A Trust Boundary Gap in AI Coding Assistants
- Inheriting the Receipts: Securing the AI Your Company Already Adopted
- Model-agnostic AI is key to business continuity as models keep changing
- The Vulnerability Curve Bent With the AI Curve
- AI is writing more of your Terraform
- Pickle in the Middle – Hijacking Vertex AI Model Uploads for Cross-Tenant RCE
- Captured Logs Reveal Hackers Using Claude and Codex to Breach Companies
- AWS Security Digest #265 - Promises
- Everyone Is Buying AI Guardrails. But Agents Have the Keys to the Car.
- The sorry state of skill distribution
- Let’s talk about encrypted reasoning
- Investigating suspicious AI workflows in Microsoft Entra Agent ID: Autonomous agents
- Comparing AI Application Security Testing Platforms
- Exploring Agent based Cloud Review Capabilities
- Negative-Days with Vulnerability Spoiler Alert: Three Months Later
- How to Secure Your Enterprise LLM Deployment
- Bypassing LLM Supervisor Agents Through Indirect Prompt Injection
- How We Cut LLM Costs by 59% With Prompt Caching
- Cracks in the Bedrock: Agent God Mode
- AI in cybersecurity: The good, the bad, and the FUD
- What is LLM Penetration Testing? A Complete Guide