October 13, 20266 min read
OSS Scanner Finds Bugs. Maintainers Still Own the Fix.
Anthropic's new service sends vulnerability reports without human review. The useful test is how much work it takes to turn those reports into verified fixes.
Research / Tag
ai-security
26 articles tagged ai-security
August 9, 202610 min read
Both Frontier Labs Broke Containment. The Exploits Were Boring.
OpenAI's evaluation model escaped a sandbox and reached Hugging Face production, Anthropic's reached three real companies, and a Chinese actor drove DeepSeek through Hermes at 460 targets. Not one of them needed a novel exploit.
August 10, 202618 min read
OpenAI Paused Astra for Cyber Risk, Then Sold Cyber Access
OpenAI said on August 7 it cannot rule out Critical cyber capability in Astra, and on August 10 shipped GPT-5.6-Cyber at 95% completion on exploit-chain and privilege-escalation requests through sixteen resellers. Progress LoadMaster CVE-2026-8037 reached KEV as a pre-auth RCE at CVSS 9.6, and Exfil
August 25, 202622 min read
Three AI Attacks This Week, Not One New Way In
Wiz's Red Agent autonomously found and exploited a GitHub Actions script injection in Snowflake's snowflake-connector-net and read the company's internal Jira, on a workflow GitHub Advanced Security had already scanned and cleared. Five federal agencies warned that AI-written scripts are driving pyt
September 9, 202617 min read
AI Agents Got New Safeguards. Old Access Bugs Still Work.
Adobe's CVSS 10.0 Commerce flaw is being exploited. LiteLLM's MCP authentication bypass is now KEV-listed. Unit 42 reports an attacker using a victim's AI endpoints after compromise. Meanwhile Claude Code patches execution boundaries, Anthropic proposes customer-controlled monitoring storage, and Google packages Gemini with CodeMender for trusted defenders.
August 9, 20265 min read
The Autonomous Part Was The Part That Failed
Unit 42 recovered a full offensive AI session because the agent served its own operator to the internet, and the transcript shows where the automation stopped working
August 11, 20265 min read
When Your AI Red Team Becomes Your SOC
Detection infers that something happened. Exploitation proves what is possible. We are pouring agents into the half that can only ever guess, and leaving the half that produces receipts to a quarterly pentest.
August 21, 20266 min read
The Agent Never Broke the Sandbox. It Didn't Have To.
Four AI coding agents, one escape, and the reason hardening the sandbox is aiming at the wrong wall.
August 26, 20266 min read
Everything Is a Plugin Is a Security Statement
DeepSeek's harness writes down what every agent runtime has quietly asked you to trust, and being able to read it is the most useful thing about it.
August 31, 20265 min read
Your Agent's Memory Is a Supply Chain
Persistent identity files turn one compromised agent into a writer inside the next agent's trusted context.
September 9, 20267 min read
Using Astra? Here's What It Can Do, and the Story Behind It.
The benchmarks explain the excitement. The deployment details explain why your experience may be different.
August 8, 202611 min read
The Attacker Stopped Being a Person
Point the try-score-rewrite loop at your own product before a stranger points one at it, and put your judge under harder scrutiny than your generator
August 10, 202614 min read
What the Red Team Demos Don't Show You
A real overnight run produced 41 findings. Eleven were real, thirty were invented, and three targets were touched that should never have been touched. Here is how to run an autonomous agent so that arithmetic works for you.
August 17, 202614 min read
You Do Not Fix an Agent by Making It Smarter
Every autonomous agent fails in the same seven ways, and the order is predictable because the same conditions trigger each one. Every fix is the same move: take the creative core you cannot trust and wrap it in something deterministic that you can.
August 31, 20269 min read
Don't Try to Make an Agent Deterministic
A serious agent needs a playbook, a harness, hard boundaries, and an operator who owns the decisions the system cannot score.
June 9, 20267 min read
Everyone Selling You an AI Agent Isn't Telling You the Whole Truth
The word agent gets used for a chatbot with a system prompt, a script in a loop, and a system that plans and acts on its own. Three different animals. Only one can hurt you. A red teamer's guide to what an AI agent actually is and what agentic really means.
June 10, 202613 min read
Agentic AI Is a Weapon You Can't Aim
The autonomy that lets an agent clear your overnight queue is the same autonomy that lets one poisoned document turn it against you. One property, two sides. Why the more agentic the system, the further a single injection travels.
June 10, 202610 min read
Your AI Agent Is Chaos. Tame It.
You will never make the model deterministic. So stop trying. You make the system around it deterministic, shrink the part that needs judgment to almost nothing, and put a fence around what's left. Here is how that actually works.
June 10, 202611 min read
How Do You Actually Hack an AI?
Prompt injection, jailbreaks, exfiltration, poisoning, tool abuse, excessive agency. The map of how every AI system breaks, whether you are attacking one or defending your own agent. A red teamer's working taxonomy.
April 24, 20265 min read
Why MCP Is the Shadow IT of AI
Every team is wiring agents to MCP servers with the same casual trust they once showed Dropbox installs. The attackers have already noticed.
March 18, 202610 min read
Your First AI Red Team Skill: From Zero to Weaponized in 30 Minutes
Claude Code is the best AI tool I've found for offensive security, but these concepts work with Gemini and other powerful AI agents too. Here's how to build your first AI red team skill and why it changes everything about how you operate.
March 19, 202613 min read
Building Adversarial Agents: Your First AI Hackbot
Most AI security tools test for prompt injection with a list of 50 known payloads. That's a scanner, not a pentester. Here's how to build an AI that actually thinks like an attacker.
March 19, 202614 min read
The RAG Attack Playbook: Poisoning the Knowledge Base
Your company's AI chatbot trusts its vector database like gospel. I can change what it believes with a single document. Here's how RAG attacks work and how to test for them.
March 19, 202615 min read
Agent Kill Chains: When Jailbreaking Gets Dangerous
A jailbroken chatbot says something embarrassing. A jailbroken AI agent with database access and API keys does something catastrophic. Here's how to test agent security before an attacker does.
March 19, 202613 min read
Coordinated Operations: Multi-Agent Red Team Campaigns
One AI agent found the vulnerability. A second built the exploit. A third exfiltrated the data. The whole operation took 4 minutes. Here's how to run coordinated AI red team operations.
March 19, 202614 min read
The AI Pentest Report: From Raw Findings to Executive Deliverable
The hardest part of any pentest isn't finding the vulnerabilities. It's explaining them to someone who doesn't know what a prompt injection is. Here's how AI generates better reports than most consultants.