Aikido
Start for Free
No CC required

Research

Subscribe to hear about critical security incidents

We'll send you updates on incidents as and when they happen
Featured
August 25, 2026

Could OpenClaw have actually hacked that Australian gym? We decided to test it.

We recreated the viral AI gym hack in a controlled environment. Running Opus 4.6 on OpenClaw, the model exploited the booking flaw in nine of ten runs.

#AI

#AI Safety

#open-source

#IDOR vulnerabilities

August 24, 2026

How Aikido finds more vulnerabilities than Mythos at half the cost

Aikido AI Code Audit found 8 more vulnerabilities than Claude Security with Mythos at less than half the cost. How harness design drives coverage per dollar.

#AI Penetration Testing

#AI

#Mythos

July 16, 2026

Benchmarking 13 AI models on rediscovering known CVEs

We tested 13 AI models against 26 known CVEs to see which finds the most vulnerabilities — and whether the priciest model is worth the cost.

#AI Penetration Testing

#AI

Subscribe to our newsletter.
No spam, guaranteed.

Aikido Libraries
Data Security
Hardened images
GitHub Security
Mythos
Aikido Device Protection
Aikido Endpoint
Pypi
Secrets
Aikido Zen
IDOR vulnerabilities
IDE Security
Announcements
European Cyber Security
Continuous Pentesting
AI Safety
Self-securing Software
SSDLC
VS Code
AI Penetration Testing
Threat Modeling
Cyber Resilience Act
Triaging
AutoTriage
Pentesting
Bazel
Code Quality
OWASP
NIS2
Legaltech
fintech
RASP
End of Life
SQL Injections
DAST
cnapp
CSPM
ASPM
Infrastructure as a Code IaC
Network Security Monitoring
License Scanners
SBOM
Container Scanning
AppSec
Vulnerabilities
Software Supply Chain Security
API
Dependencies
Continuous Security Monitoring
DevSecOps
Vibe Coding
AI
NPM
autofix
Malware
Article
open-source
SCA
intel
SOC 2
usecase
Tools
SAST
Compliance
CircleCI
Codeship
IMDSv2
Cloud
IMDSv1
SSRF
AWS
August 25, 2026

Could OpenClaw have actually hacked that Australian gym? We decided to test it.

We recreated the viral AI gym hack in a controlled environment. Running Opus 4.6 on OpenClaw, the model exploited the booking flaw in nine of ten runs.

Tags/

#AI

#AI Safety

#open-source

#IDOR vulnerabilities

August 24, 2026

How Aikido finds more vulnerabilities than Mythos at half the cost

Aikido AI Code Audit found 8 more vulnerabilities than Claude Security with Mythos at less than half the cost. How harness design drives coverage per dollar.

Tags/

#AI Penetration Testing

#AI

#Mythos

August 21, 2026

We burned 11.7bn tokens to find the best cyber AI model

We tested 10 AI models on 32 fresh CVEs. DeepSeek V4 Pro found 28, and three cheap runs beat one pass of Opus 5 or Grok on total coverage.

Tags/

#AI

#AI Penetration Testing

July 16, 2026

Benchmarking 13 AI models on rediscovering known CVEs

We tested 13 AI models against 26 known CVEs to see which finds the most vulnerabilities — and whether the priciest model is worth the cost.

Tags/

#AI Penetration Testing

#AI

Vulnerabilities & Threats

Real-world CVE breakdowns, malware analysis, exploits, and emerging risks.

See all

News

Our perspective on the stories shaping software security right now

See all

Research

Our in-depth research including benchmarks, comparisons and testing.

See all

Product & Company Updates

What’s new at Aikido—from product launches to big security wins.

See all

Guides & Best Practices

Actionable tips, security workflows, and how-to guides to help you ship safer code faster.

See all

Compliance

Stay ahead of audits with clear, dev-friendly guidance on SOC 2, ISO standards, GDPR, NIS, and more.

See all

Get secure now

Secure your code, cloud, and runtime in one central system.
Find and fix vulnerabilities fast automatically.

Start Scanning
Book a demo
No credit card required | Scan results in 32secs.