ai-agents
20 pieces
Field Guide to AI, Security and Cybercrime
AI Agents Are a New Kind of Insider
Insider-threat programmes look for a person with a motive. An agent holds the same access with no motive at all, and can be turned by what it reads.
Opinion · 7 min
AI Agents Do Not Sleep: The End of the Right to Disconnect
Autonomous AI agents create a permanent, silent workstream that makes the legal right to disconnect impossible to enforce.
Opinion · 8 min
BragJack: How a Browser Extension Hijacks Your AI Assistant's Trust
A malicious browser extension can impersonate the trusted channel between your AI assistant and its vendor, gaining its elevated privileges.
Opinion · 6 min
Chatbot Memory: What Your AI Assistant Keeps About You
Your assistant keeps three separate records about you. Deleting one does not delete the others.
Opinion · 6 min
How AI Agents Turn Bad Sources Into Confident Actions
An agent does not just repeat misinformation; it converts it into actions and documents that carry your organisation's authority.
Opinion · 7 min
The Lethal Trifecta: When an AI Agent Can Read, Be Steered and Send
Why combining private data access, untrusted content exposure, and external communication guarantees exploitable agents.
Opinion · 8 min
Verifying the Identity of an AI Agent You Cannot See
When an AI acts on your behalf, how does a third party know it's authorised and not a spoof?
Opinion · 8 min
AI Coding Assistants and Leaked API Keys: Where Secrets Escape
Secrets now leak through context windows and logs, not only through commits.
Opinion · 9 min
AI in the Security Operations Center: What It Actually Speeds Up
Summaries and triage help analysts; autonomous response amplifies every false positive.
Opinion · 9 min
AI Red Teaming for Small Teams: A One-Week Plan
Test what your AI features can do when fed hostile content, not how rude a jailbreak can make them.
Opinion · 9 min
AI Shopping Agents: The Missing Proof You Approved the Purchase
Card protections assume a human clicked buy; delegated agents break that assumption.
Opinion · 8 min
An AI Agent Kill Switch: Design the Stop Button First
Most deployments cannot halt one agent mid-task without killing everything else.
Opinion · Field note · 8 min
Are AI Browsers Safe? The Logged-In Session Problem
An agent that browses as you inherits every account you are signed in to.
Opinion · 9 min
MCP Server Security: A Config File Is Now Executable Code
Cloning a repository can launch tools with your privileges before you have read a line.
Opinion · 9 min
Non-Human Identities: The Credentials Nobody Owns
Service accounts, API keys and tokens outnumber people, and most have no owner or expiry.
Opinion · 8 min
Running a Local LLM for Privacy: What You Gain and What You Don't
Local models remove the provider from the picture, not the risks of what the model is allowed to do.
Opinion · Field note · 8 min
Slopsquatting: When AI Invents a Package, Someone Registers It
Hallucinated dependency names repeat across users and sessions, which makes them predictable targets.
Opinion · 10 min
Vibe Coding Security Risks: The Check That Was Never Written
AI-generated apps rarely fail through exotic bugs; they fail through omissions nobody asked for.
Opinion · 8 min
What Is Prompt Injection? Why It Is Not Like SQL Injection
The comparison suggests a patch exists; the architecture says otherwise.
Opinion · 9 min
When AI Agents Talk to Each Other, Who Is in Charge?
Delegation chains can launder a stranger's instruction into something that looks authorised.
Opinion · 9 min