Sign in Subscribe
AI Security

AI Security

Articles covering AI and machine learning security threats, including shadow AI risks, LLM vulnerabilities, prompt injection attacks, and strategies for securing AI systems in enterprise environments.
18
Aug
MCP Security Best Practices: Check Your Own Server First

MCP Security Best Practices: Check Your Own Server First

19 August 2026. Checked against MCP specification 2026-07-28. Most MCP security best practice do not go far enough.
10 min read
20
Jul
Hugging Face's AI breach needed AI to investigate it. The models refused.

Hugging Face's AI breach needed AI to investigate it. The models refused.

Updated 21 August 2026: rewritten to cover all four evaluation disclosures. An earlier version said hosted models refuse forensic work
10 min read
05
Jul
LiteLLM Security: Your AI Gateway Is a Secrets Manager. Benchmark It Like One

LiteLLM Security: Your AI Gateway Is a Secrets Manager. Benchmark It Like One

July 2026 An AI gateway is a secrets manager wearing a router's clothes. LiteLLM, the most widely adopted
7 min read
03
Jul
Your AI Coding Assistant's Config Folder Is a Persistence Surface

Your AI Coding Assistant's Config Folder Is a Persistence Surface

Supply-chain malware started writing into the config files your coding agent reads on every run. Nothing in the usual toolchain is watching that surface.
10 min read
01
Jul
The EU AI Act as an engineering machine: build requirements, high-risk use case tiles, provider and deployer roles, an August 2026 deadline, and euro penalty weights.

The EU AI Act Lands on Your Codebase, Not Just Your Legal Team

July 2026 The EU AI Act for developers and technical teams The EU AI Act describes engineering work. Risk management,
6 min read
20
Jun
The Agent Control Plane: Security's Third Sprawl

The Agent Control Plane: Security's Third Sprawl

June 2026 Every major platform vendor is shipping an agent control plane this year, and most of them are selling
9 min read
20
Jun
Claude Code welcome screen with its pixel-art night scene and the terminal theme selection menu.

Claude Code Security Review: CodeGuard vs the Built-in Tools

June 2026 Claude Code can review your code for security flaws. Type /security-review and it scans your project for
6 min read
20
May
Exposed AWS Credentials Are Used in Under 90 Seconds: Findings from AI Infrastructure Research

Exposed AWS Credentials Are Used in Under 90 Seconds: Findings from AI Infrastructure Research

Exposed AWS credentials were used against live AWS APIs within 67 seconds of being harvested, faster than CloudTrail delivers the first event to a defender.
9 min read
14
May
The Scanners Mapping AI Infrastructure Aren't After Your Model. They're After Your Credentials.

The Scanners Mapping AI Infrastructure Aren't After Your Model. They're After Your Credentials.

460 source IPs, 11,643 requests, 72 hours against exposed AI infrastructure. The operators that recognised it were cataloguing; the ones attacking were after credentials that sit on any exposed host.
7 min read
14
Apr
A glasswing butterfly resting on a green leaf, its transparent wings revealing the leaf surface beneath

Anthropic expected six months of lead on Claude Mythos. It got twenty days.

Last updated: 21 August 2026. What's changed: the export controls were lifted on 30 June and Fable 5
8 min read