Pre-auditThree days of senior audit time for $1,500, credited in full toward your Zealynx audit.3 audit days, credited toward your auditSee how →

Adversarial & AI Security.

AI security, MCP server reviews, and red-team write-ups across smart contracts, dApps, and Web2 infrastructure.

TOPIC
All56AI Security13MCP Security9Red Teaming28Agent Security5
AI Agent Outbound Authority: Audit Checks
AI securityMay 20

AI Agent Outbound Authority: Audit Checks

13 min read
OWASP ASI02 Explained: AI Agent Tool Misuse Attacks
AI securityMay 19

OWASP ASI02 Explained: AI Agent Tool Misuse Attacks

OWASP Agentic Top 10 · Part 2 of 10
Indirect prompt injection: the Web3 agent attack chain
AI securityMay 15

Indirect prompt injection: the Web3 agent attack chain

26 min read
AI Agent Approval Bypass: Audit Checks
AI securityMay 13

AI Agent Approval Bypass: Audit Checks

12 min read
Supply Chain Attacks in Web3 — From NPM to Protocol Exploits
AI securityMay 6

Supply Chain Attacks in Web3 — From NPM to Protocol Exploits

12 min read
JailBreak Technique: Misguided Attention Using Trolley Problem
AI securityMay 5

JailBreak Technique: Misguided Attention Using Trolley Problem

13 min read
Social Engineering Models: The Polite Approach
AI securityApr 29

Social Engineering Models: The Polite Approach

12 min read
OpenClaw Security Guide: Prompt Injection, Malicious Skills, Hardening
AI securityJan 2026 · Updated Apr 2026

OpenClaw Security Guide: Prompt Injection, Malicious Skills, Hardening

19 min read
Why AI security needs pentesting, red teaming, and audits together
AI securityApr 7

Why AI security needs pentesting, red teaming, and audits together

20 min read
AI trading bot security: 5 critical attack vectors in DeFi
AI securityMar 30

AI trading bot security: 5 critical attack vectors in DeFi

21 min read
When AI controls DeFi vaults, prompt injection becomes remote code execution
AI securityMar 25

When AI controls DeFi vaults, prompt injection becomes remote code execution

16 min read