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.
20
Jul
An AI agent breached Hugging Face. Frontier models refused to investigate

An AI agent breached Hugging Face. Frontier models refused to investigate

An autonomous agent ran the whole attack. The defenders' frontier models refused to analyse it. The asymmetry, made concrete.
3 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

Fable 5 Is Frozen and Glasswing Still Leaves Two Problems Open

Last updated: 30 June 2026 | What's changed: both models were suspended on 12 June under a US export
8 min read
04
Apr
Laptop displaying code in a dark environment with blue and pink lighting, illustrating the developer tooling decisions at the centre of Anthropic's OpenClaw subscription change.

Anthropic Cuts OpenClaw Off Claude Subscriptions And It's Just the Start

Last updated: 5 April 2026 | What's changed: Initial publication covering April 4 enforcement. Get updates like this delivered
3 min read