Learn from the Geordie team

Agents are part of the mob now

A few months of pairing and mobbing with agents later (mostly engineer with engineer, sometimes across disciplines), I think most of the core principles surrounding pairing matter even more.

Who should own agent security and operations? Part 2: The division of labor

Thirteen agent security & operations tasks, and who typically owns them.

Who should own agent security and operations? Part one: Five org structures

Agents went from rogue pilots to essential workers in the space of two years, and several different ownership structures have emerged.

Value Intelligence: Connecting agent spend to security, the work, and value it returns

What do agents cost and deliver? Spend tied to the work agents perform, the value it returns and the risk security teams manage.

Are we confusing superintelligence with being human?

AI is becoming extraordinarily capable at tasks we associate with human intelligence.

Hanah Darley

We have a human-in-the-loop savior complex

Human oversight is one of the most widely recommended safeguards for AI agents, yet putting a person in charge of approving an action says very little about whether they are equipped to exercise independent judgment.

Hanah Darley

Technical Advisory: Trojanized Claude Code VS Code Extension – anthropic.claude-code 2.1.313

The Claude Code extension for VS Code was trojanized at version 2.1.313 and distributed through the Cursor Extension Marketplace for about 11 hours, planting a persistent SSH backdoor.

Colin Ife

The CISO's Guide to Agentic Security and Operations

How security leaders run an agent estate that is already doing the business's work, from the first inventory to a program that scales.

Hanah Darley

Behavioral observability: Keeping a record of what every agent does

What did the agent actually do?

When the agent rewrites its own configuration

Security teams approve a coding agent by looking at how it is set up, which sandbox is on, which tools and MCP servers it can reach, and what it is allowed to run, and that approval rests on an assumption that the setup will still be the setup the next time anyone looks.

Beam: Guiding agents as they work, with tiered escalation

How do I reduce agent risk without stopping the work?

OWASP’s Q3 exploit roundup shows where an agent's limits are actually enforced

OWASP’s Q3 exploit roundup says prompt-level instructions alone do not establish a secure boundary.

Hanah Darley

Agent behavior comes from more than the model

Model capability is one input to what an agent does.

Hanah Darley

Shadow agent activity crossed an organizational boundary

An AI agent was being used to mine Bitcoin.

A supply-chain incident made an AI coding blind spot visible

Their EDR had no record of the activity.

Personal agents act without being asked

One personal agent posted a user's private financial audit into his company's exec Slack channel.

Hanah Darley

What happens when an agent tampers with its own record?

With agents our industry has a chain-of-custody problem.

Benji Weber

Personal agents, shared platforms, and unintended disclosure

Shane Mac’s account of an agent posting his bank balances into his company’s executive Slack channel is worth reading closely.

Hanah Darley

How security teams can operationalize the OWASP Agentic Skills Top 10

OWASP’s new Agentic Skills Top 10 gives security teams a shared vocabulary for agent skills.

Shelved agents and the case for agentic lifecycle management

When enterprises iterate on their agent workflows, older agents rarely get decommissioned.

Understanding the cost, the output, and the ownership gap across your agentic workforce

What 50+ organizations running agents in production told us about agent spend, who owns it, why the bill doesn't explain itself, and what to do instead of freezing.

What the agent security market watches, and what it still can't see

Each agent security category extends the layer it was already built to watch.

The hidden cost (and savings) of AI agent skills

The same agent capability can cost ~10,000 tokens as an MCP server or ~100 as a skill.

Geordie

The Golden Catalog Is a Comforting Fiction

Pre-approved agent template libraries optimize for control over a static asset, when the thing they're trying to control isn't static at all.

Hanah Darley

Why (and how) we're helping customers connect agent spend to the agent work driving it

Move from uncertainty to informed confidence on both risk and spend, with cross-platform spend aggregation and token-efficiency mapping.

Hanah Darley

Geordie Launches Cost Intelligence to Connect AI Spend to the Agent Work Driving It

New capability gives AI Ops teams a clearer picture of the financial risk behind agent activity.

Geordie

Refusal Training Has a Blind Spot: Skills Run Before the Model Reasons

A malicious skill called Clawsights ran a shell command before Claude Code's model ever reasoned about it.

Hanah Darley

A guide to agent skills

A working model for where agent skills actually create risk, and six practices for folding them into the governance you already run.

A Guide to Agent Control

Geordie’s Field Guide shows the control points Anthropic, OpenAI, AWS, and Microsoft have built in natively – and where each falls short.

Context as the Attack Surface: A New Class of Agent Compromise

A new academic paper shows AI agents can be compromised without a single malicious instruction, just by corrupting what the agent trusts.

Hanah Darley

After AISI, Anthropic, and OpenAI: Where Agent Governance Needs to Go Next

Four disclosures in three weeks, each one showing something new, all pointing to the same governance requirements.

Hanah Darley

MCP 2.0: How the 2026-07-28 Release Changes Agent Governance in the Enterprise

What is new and what MCP 2.0 means for security teams

Hanah Darley

Confidently Shipping Agents After OpenAI-Hugging Face

What this incident shows about governing AI agents

Giuseppe Trovato

Geordie Now Available Through GuidePoint Security

New collaboration gives GuidePoint customers access to purpose-built AI agent security and governance

Geordie

Where to Find Geordie at Black Hat 2026

Meet with the Geordie team at Black Hat USA 2026 in Las Vegas, August 1–6

Story Tweedie-Yates

Geordie Recognized as a Cool Vendor by Gartner in “Coolest Vendor Innovations in AI Software Security” Report

The company’s unique approach to securing and governing AI agents drives 50× ARR growth in the first six months of 2026

Story Tweedie-Yates

Six Practical Security and Governance Steps for Adopting Claude Cowork

How to adopt Cowork quicker using built-in configurations alongside contextual visibility and controls

Story Tweedie-Yates

The harness: three ways to secure and govern the operational infrastructure of AI agents

Matching security and governance to teams moving fast on AI agent deployments.

Story Tweedie-Yates

Skills, Plugins, and Shell Commands: The Agent Attack Surface MCP Doesn’t Cover

Three foundational principles for governing the agentic toolset

Hanah Darley

Securing AI Agents Means Following Behavior, Not Boundaries

A practical view of agent security from our work on OWASP's latest guidance.

Josh Collyer

Geordie Extends Microsoft Partnership to Support Agent Control Specification

Helping customers keep agent controls consistent as their infrastructure evolves.

Hanah Darley

Geordie Raises $30M to Help Enterprises Securely Adopt Agentic AI at Scale

AI agent security company sees 1300% ARR growth in the first five months of the year as global enterprises adopt at scale

Story Tweedie-Yates

Geordie AI Raises $30M Series A as Enterprises Race to Govern Autonomous AI Agents

Henry Comfort, CEO and co-founder of Geordie AI, on raising a $30M Series A and what it means for enterprises racing to govern autonomous AI agents.

Henry Comfort

Geordie AI Named to the 2026 CB Insights’ List of the 100 Most Innovative Artificial Intelligence Startups

Geordie is recognized for its achievements in Security and Governance for AI Agents

Story Tweedie-Yates

Geordie Extends Agentic AI Security and Governance Coverage Through Claude Compliance API

Geordie announces integration with Claude Compliance API to extend security and governance across the Claude Enterprise deployment surface

Hanah Darley

Top 10 AI Agent Governance Best Practices

Go beyond identity to a broader maturity model of prompts, guardrails and behavior

Hanah Darley

Technical Advisory: n8n - Multiple Vulnerabilities - March 2026

Two Critical RCE flaws and five High-severity vulnerabilities in n8n, exploitable by any authenticated user.

Giuseppe Trovato

Geordie AI Introduces Beam: The First AI Agent Remediation Suite with Context Engineering

Proactive security controls allow forward-looking teams to secure AI agents at scale

Story Tweedie-Yates

Prompt Injection Isn’t the Main Problem in AI Agent Security

Prompt injection gets most of the attention in AI agent security.

Hanah Darley

Technical Advisory: TeamPCP Supply Chain Campaign

A threat actor compromised the Trivy vulnerability scanner and used stolen CI/CD secrets to cascade into Checkmarx, LiteLLM, and 50+ npm packages.

Giuseppe Trovato

Where to Find Geordie AI at RSAC 2026

Meet with the Geordie AI team at RSAC 2026 in San Francisco

Story Tweedie-Yates

Geordie AI Named “Most Innovative Startup” at RSAC 2026 Innovation Sandbox

Recognized for pioneering technology that enables enterprises to safely scale AI agents

Story Tweedie-Yates

Technical Advisory: Remote Shell Backdoor in MCP Package (@lanyer640/mcp-runcommand-server)

Technical Advisory: Claude Desktop Extensions Tool Chaining Vulnerability

Security researchers disclosed a tool chaining vulnerability in Claude Desktop Extensions rated CVSS 10/10, but this represents a known risk class in agentic AI systems – not a novel attack.

Technical Advisory: Figma MCP Server Remote Code Execution Vulnerability

Technical Advisory: LangChain Serialization Injection Enables Secret Extraction

Authenticated attackers can escape n8n's Pyodide Python sandbox to execute arbitrary system commands with host privileges.

Giuseppe Trovato

Technical Advisory: Multiple Vulnerabilities in Cursor AI Code Editor

Technical Advisory: n8n Unauthenticated Remote Code Execution (Ni8mare)

Critical unauthenticated remote code execution vulnerability in n8n workflow automation allows attackers to exploit content-type confusion in Form webhook file upload processing to read arbitrary files, steal credentials, and execute arbitrary code on the server.

Giuseppe Trovato

Technical Advisory: n8n Python Sandbox Escape Enables Arbitrary Command Execution

Authenticated attackers can escape n8n's Pyodide Python sandbox to execute arbitrary system commands with host privileges.

Giuseppe Trovato

Technical Advisory: n8n Remote Code Execution via Arbitrary File Write

Critical vulnerability in n8n workflow automation allows authenticated attackers to achieve remote code execution through Git node exploitation

Giuseppe Trovato

Technical Advisory: n8n Remote Code Execution via Expression Injection

Critical remote code execution vulnerability in n8n workflow automation platform allows authenticated users to execute arbitrary code on the server through specially crafted workflow expressions that escape the sandbox isolation.

Giuseppe Trovato

Technical Advisory: Serverless Framework MCP Server Command Injection

Claude Desktop Extensions RCE Vulnerability: A Technical Analysis of Configuration Risk and Agentic AI Governance

A remote code execution vulnerability in Claude Desktop Extensions received a CVSS 10.0 score this week.

Giuseppe Trovato

AI Agent Guardrails Explained: What They Cover and What They Don't

Guardrails are often treated as a universal safety layer for AI agents, but they're not.

Hanah Darley

Geordie AI Selected as Top 10 Finalist for RSAC™ 2026 Conference Innovation Sandbox Contest

Geordie AI selected for monitoring and governing AI agents in real time.

Agentic AI Governance: Why MCP Gateways Fall Short

The autonomous nature of AI agents requires purpose-built agentic AI governance platforms.

Hanah Darley

AI Agent Risk: What Executives Need to Know to Innovate Safely and Confidently

AI Agents aren’t just software.

Hanah Darley

Governing AI Agents: Best Practices to Scale Safely

Building on research from Berkeley, this article outlines five barriers to enterprise AI adoption and the AI governance best practices to overcome them with visibility and accountability.

Hanah Darley

Building AI Agents? Here’s What Developers Want Leaders to Know

Building AI Agents promises speed and scale, but developers know the pitfalls.

Hanah Darley

Enterprise AI Governance: A Practical Roadmap to Scale AI Agents

Enterprises are experimenting with AI agents, but scaling safely requires enterprise AI governance.

Hanah Darley

From Connectivity to Collaboration: APIs, MCPs, and A2A in Agentic Plans

APIs, MCPs, and A2A form the foundation of AI Agent systems, yet their roles are often fragmented.

Hanah Darley

Geordie Wins Black Hat Europe 2025 Startup Spotlight

Geordie won the Black Hat Europe 2025 Startup Spotlight.

How to Actually Patch CVE-2025-68145, CVE-2025-68144, and CVE-2025-68143 in mcp-server-git

A practical, deployment-level guide to patching recent mcp-server-git CVEs - explaining how uvx caching, pip installs, and outdated Docker images can leave systems vulnerable, and how to verify you’re actually fixed.

Giuseppe Trovato

Making AI Accountable: How Explainability and Observability Meet Regulation and Trust

AI adoption is accelerating, but trust and accountability are essential.

Hanah Darley

How The Next MCP Release Shapes Agentic AI in Enterprise

What the next Model Context Protocol (MCP) release means for enterprise security and risk teams running AI agents in production.

Hanah Darley

Moving Beyond Static Prompts to Living Playbooks: What ACE Means for Enterprise AI Governance

ACE moves enterprise AI governance beyond static prompts to living playbooks.

Hanah Darley

OpenClaw and the Emergence of Personal AI Autonomy Infrastructure

Why OpenClaw matters less as a vulnerability story and more as a signal that personal autonomous agents have arrived.

Hanah Darley

Rethinking Security: The Limits of Endpoint Controls in an AI Agent World

Endpoint controls like EDR and XDR remain critical to enterprise defense, but they weren’t built for AI Agents.

Hanah Darley

Seeing the Risks Clearly: How Leaders Can Evaluate AI Investments with Confidence

AI adoption is accelerating, but not every investment is safe.

Hanah Darley

Technical Advisory: Multiple High-Severity Vulnerabilities in n8n

Eight high-to-critical n8n vulnerabilities disclosed in February 2026 invalidate earlier patching guidance.

Giuseppe Trovato

The New Attack Surface: Why AI Agents Need Taint Analysis

As AI Agents evolve into autonomous actors, securing them requires techniques beyond identity and access controls.

Colin Ife

Understanding Recent n8n Vulnerabilities: Exposure, Risk, and Remediation

A practical breakdown of recent n8n vulnerabilities, explaining exposure, risk, and how to choose the right remediation path.

Giuseppe Trovato

Unlocking Safe Innovation: Why AI Agents Must Be Transparent

AI Agents can’t be black boxes.

Hanah Darley

Why We're Building Geordie

We started Geordie to build the governance layer for AI agents.