Zealynx research
Security Research.
Public write-ups on the bugs, patterns, and protocols we audit. Engineer-to-engineer, no fluff.
48 results for "AI Agents"
Clear search Search.
Agentic DeFi security: when AI agents control treasury, trading, and liquidations
21 min read
MCP Security Guide: 24 Checks for AI Agents & MCP Servers
9 min read
OpenClaw Security Guide: Prompt Injection, Malicious Skills, Hardening
19 min read
How to Build Your Own AI Auditor Agent (Interactive Guide, Multiple Paths)
15 min read
DeFi Audit Process 2026: Secure Code with AI Tools
8 min read
AI Agent Wallet Security: 5 Ways Someone Empties It (and the Fix for Each)
20 min read
x402 Security: 5 Ways a Paid API Gets Drained (and the Fix for Each)
16 min read
Long-Lived Agents: Delayed Execution Risk
14 min read
OWASP ASI10 Explained: Rogue Agents and Misalignment
OWASP Agentic Top 10 · Part 10 of 10
OWASP ASI09 Explained: Human-Agent Trust Exploitation
OWASP Agentic Top 10 · Part 9 of 10
OWASP ASI03 Explained: AI Agent Identity & Privilege
OWASP Agentic Top 10 · Part 3 of 10
When AI controls DeFi vaults, prompt injection becomes remote code execution
16 min read
Postmark MCP Supply-Chain Attack: ASI04 in Production
12 min read
Indirect prompt injection: the Web3 agent attack chain
26 min read
AI trading bot security: 5 critical attack vectors in DeFi
21 min read
Solidity Smart Contract Audit 2026: Pricing, AI & Readiness Manifesto
9 min read
Our AI Pipeline Finds Criticals Hiding in Plain Sight
17 min read
JailBreak Technique: Misguided Attention Using Trolley Problem
13 min read
How to Harden an MCP Server Before It Becomes a Master Key to Your Infrastructure
21 min read
OWASP ASI06 Explained: AI Memory & Context Poisoning
OWASP Agentic Top 10 · Part 6 of 10
OWASP ASI01 Explained: AI Agent Goal Hijacking
OWASP Agentic Top 10 · Part 1 of 10
OWASP ASI02 Explained: AI Agent Tool Misuse Attacks
OWASP Agentic Top 10 · Part 2 of 10
OWASP ASI04 Explained: Agentic Supply Chain Attacks
OWASP Agentic Top 10 · Part 4 of 10
Why AI security needs pentesting, red teaming, and audits together
20 min read
Why AI Red Teaming Is No Longer Optional in Today's Security Landscape
9 min read
Cognitive Psychology Reveals LLM Vulnerabilities: AI Security Foundations
LLM Security Deep Dive · Part 1 of 4
Auditing AI Trading Bots: Security Framework
16 min read
Cursor IDE MCP CVEs: MCPoison & CurXecute Explained
11 min read
Still building? What to settle before you scope an audit
14 min read
Token Management: Securing Against Token Waste
6 min read
MCP Vulnerabilities 2025-2026: 16+ CVEs & Breach Index
14 min read
EscapeRoute Explained: Anthropic Filesystem MCP CVEs
13 min read
AI Agent Outbound Authority: Audit Checks
13 min read
AI Agent Approval Bypass: Audit Checks
12 min read
Safeguard: Analysis of Customer Agent Orchestration System
26 min read
OWASP ASI05 Explained: AI Agent RCE Patterns
OWASP Agentic Top 10 · Part 5 of 10
How Gradient Descent, KL Divergence & Graph Topology Let Attackers Poison Your AI Model
LLM Security Deep Dive · Part 3 of 4
Debugging AI Psychosis: Hallucination
18 min read
Why AI Penetration Testing Is Now Critical in Web3 Security
7 min read
When LLMs Sign Transactions: AI-Driven Smart Contract Threat Model
15 min read
OWASP ASI08 Explained: Cascading Failures in Agentic Systems
OWASP Agentic Top 10 · Part 8 of 10
CVE-2025-49596: Anthropic MCP Inspector RCE Explained
12 min read
ERC-4337 Smart Accounts: Six Failure Modes We're Already Seeing in Audits
14 min read
OWASP ASI07 Explained: Insecure Inter-Agent Communication
OWASP Agentic Top 10 · Part 7 of 10
Anthropic MCP SDK Vulnerability (April 2026): Full Analysis
12 min read
Social Engineering Models: The Polite Approach
12 min read