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
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
Inside the Scanners Hunting Exposed AI Infrastructure: 72 Hours of Findings

Inside the Scanners Hunting Exposed AI Infrastructure: 72 Hours of Findings

460 source IPs, 11,643 requests, 72 hours. The AI-aware operators in the data enumerated; the exploitation observed targeted credentials, not AI capabilities.
19 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: 20 June 2026 | What's changed: Mythos Preview became Fable 5 and Mythos 5 on 9 June,
7 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
31
Mar
A ginger cat viewed from behind, sitting in front of a blurred monitor displaying code

What Censys's OpenClaw Count Reveals That February's Headlines Did Not

31st March 2026 OpenClaw's internet-facing exposure has fallen sharply since the February 2026 peak. Public scrutiny, repeated
9 min read
12
Mar
SOC Analyst Role is changing ?

Will AI Replace SOC Analysts?

March 2026 LinkedIn Post Copy Link Large language models cannot yet be trusted to make autonomous security decisions. That is
10 min read
01
Mar
Concrete brutalist structure where four beams meet at a central junction that has cracked and fractured, showing how AI agent supply chain risk concentrates at the connection points.

AI Agent Security Risks in 2026: The Incident Landscape and Hardening Framework

In February 2026, the supply chain threat model arrived in AI agent infrastructure all at once. The Model Context Protocol is the connective tissue across every major incident. Here's what practitioners need to know.
17 min read
05
Feb
OpenClaw security risks concept showing hidden keyboard under torn paper, representing malicious skills, exposed instances, and system-level vulnerabilities in AI agents.

OpenClaw Security Risks: Malicious Skills, Exposed Instances and Real Exploits

Latest updates (March 2026): NemoClaw announced, CVE count now 60+, and independent analysis using Censys identified 63,070 live instances
20 min read