New

EU AI Act: Digital Omnibus verschiebt Hochrisiko-Deadline

April 2026 · 6 min read
EU AI Act Digital Omnibus KMU Compliance

Die EU diskutiert eine Verschiebung der Hochrisiko-Deadline von August 2026 auf Dezember 2027. Was bereits gilt, was sich aendert, und warum Warten keine Strategie ist.

Conway: What Anthropic's Always-On Agent Means for AI Security

April 2026 · 7 min read
Conway Always-On Agent Webhook Security

Anthropic's leaked Conway project reveals an always-on persistent AI agent with webhooks, browser control, and custom extensions. The attack surface just expanded by an order of magnitude.

What the Claude Code Source Leak Teaches Us About AI Agent Security

April 2026 · 8 min read
Claude Code Source Leak AI Agent Security

512,000 lines of Claude Code leaked via npm. Two CVEs followed within days. Fake repos spread malware. What every AI team needs to know about securing their agent infrastructure.

We Scanned 11,529 MCP Servers for Security Vulnerabilities

March 2026 · 12 min read
MCP Security Registry Scan Data Study

We scanned every server in the official MCP Registry for security vulnerabilities. 850 flagged, 0 malicious patterns, and an independent validation of academic research at 6x scale.

We Scanned 11,529 MCP Servers for EU AI Act Compliance

March 2026 · 10 min read
EU AI Act Compliance MCP Security

The largest EU AI Act compliance study of MCP servers ever conducted. 11,529 servers scanned, 850 flagged. 7.4% non-compliance rate. 134 days until the deadline.

OWASP MCP Top 10 Mapping — How ClawGuard Covers Every Category

March 2026 · 8 min read
OWASP MCP Top 10 Coverage

A complete mapping of ClawGuard Shield's 225 security patterns to the OWASP MCP Top 10 standard. The only scanner covering all 10 categories plus EU AI Act compliance.

We Scanned 4,113 MCP Servers from the Official Registry — Here's What We Found

March 2026 · 5 min read
MCP Security Registry Scan Data Study SSRF

We scraped the entire MCP registry (11,529 entries), resolved 4,113 unique servers, and ran static pattern analysis. 65 servers flagged across 81 findings.

The Shared Responsibility Model for MCP Security: Why “Not My Problem” Doesn't Work

March 2026 · 12 min read
MCP Security Shared Responsibility OWASP

After filing 32 security advisories to MCP server maintainers, we identified 4 recurring pushback patterns. Here's why MCP security requires a shared responsibility model.

ClawGuard vs Cisco DefenseClaw — Two Approaches to MCP Security

March 2026 · 10 min read
MCP Security Comparison Cisco

Cisco launched DefenseClaw at RSA 2026. Here's how the two open-source MCP security scanners compare on latency, EU AI Act compliance, and architecture.

12 Prompt Injection Evasion Techniques (And How We Detect All of Them)

March 2026 · 10 min read
Evasion Prompt Injection Defense

Attackers bypass AI security scanners using leetspeak, Unicode tricks, Base64, and cross-language mixing. We built 12 preprocessors to catch them all.

6 Real MCP Security Breaches That Already Happened

March 2026 · 8 min read
MCP Security Breaches Case Studies

MCP security isn't theoretical. These 6 real-world incidents show what happens when AI agents interact with untrusted tools without runtime protection.

9 MCP Security Scanners Compared

March 2026 · 10 min read
Comparison MCP Security Tools

A technical comparison of 9 MCP security scanners. Architecture, detection approach, latency, language support, and EU AI Act coverage side by side.

7.2% of MCP Servers Have Security Vulnerabilities

March 2026 · 12 min read
MCP Security Research AI Security

We analyzed 1,899 MCP servers from the Queen's University study. 7.2% had at least one security vulnerability. Tool poisoning, credential exposure, and prompt injection are the top threats.

42 Ways to Attack an AI Agent

March 2026 · 15 min read
Prompt Injection Attack Patterns AI Security

A complete catalog of 42 prompt injection attack patterns across 5 categories. From basic role hijacking to advanced data exfiltration. Every pattern detectable in under 6ms.

Why Regex Beats LLMs for Prompt Injection Detection

March 2026 · 8 min read
Regex vs LLM Architecture

LLM-based prompt injection detection is slow, expensive, and vulnerable to the same attacks it tries to detect. Here's why deterministic regex patterns are the better first line of defense.

We Tested 18 Prompt Injection Attacks Against Our Own Scanner

March 2026 · 8 min read
Prompt Injection Security Testing

We built an open-source prompt injection scanner and attacked it with 18 real-world payloads. From 33% to 83% detection in a single afternoon, with zero false positives.