✕ Clear all filters
9 articles
▶ Videos →

📰 Dev.to · Dockfix Labs

9 articles · Updated every 3 hours · View all reads

All Articles 117,238Blog Posts 125,145Tech Tutorials 29,973Research Papers 23,710News 17,259 ⚡ AI Lessons
I Built an AI Agent Security Scanner. Semgrep and CodeQL Detect 0 Percent of These Attacks
Dev.to · Dockfix Labs 🤖 AI Agents & Automation ⚡ AI Lesson 6d ago
I Built an AI Agent Security Scanner. Semgrep and CodeQL Detect 0 Percent of These Attacks
I have spent the last 6 hours building what I believe is the most comprehensive AI agent security...
View lesson → + Playlist
AgentGuard vs Semgrep vs CodeQL: 100 Percent vs 0 Percent on AI Agent Security
Dev.to · Dockfix Labs 🤖 AI Agents & Automation ⚡ AI Lesson 6d ago
AgentGuard vs Semgrep vs CodeQL: 100 Percent vs 0 Percent on AI Agent Security
I ran the same 39 AI agent security samples through three scanners: AgentGuard, Semgrep, and...
View lesson → + Playlist
I Opened 3 Security Issues on Microsoft AutoGen and LlamaIndex. Here Is Why
Dev.to · Dockfix Labs 🤖 AI Agents & Automation ⚡ AI Lesson 6d ago
I Opened 3 Security Issues on Microsoft AutoGen and LlamaIndex. Here Is Why
I just opened 3 security issues on two of the most popular AI agent frameworks on GitHub (combined...
View lesson → + Playlist
I Scanned 3 Major AI Agent Frameworks. Here Are the 332 Critical Vulnerabilities
Dev.to · Dockfix Labs 🤖 AI Agents & Automation ⚡ AI Lesson 6d ago
I Scanned 3 Major AI Agent Frameworks. Here Are the 332 Critical Vulnerabilities
I scanned three of the most popular AI agent frameworks with AgentGuard v0.6.1. The results were...
View lesson → + Playlist
Memory Poisoning: The AI Agent Attack Vector Nobody Is Scanning For
Dev.to · Dockfix Labs 🤖 AI Agents & Automation ⚡ AI Lesson 6d ago
Memory Poisoning: The AI Agent Attack Vector Nobody Is Scanning For
Prompt injection is single-turn. You send malicious text, the agent misbehaves, next request it...
View lesson → + Playlist
Across Function Boundaries: Why Single-Function Taint Analysis Fails
Dev.to · Dockfix Labs 🛡️ AI Safety & Ethics ⚡ AI Lesson 6d ago
Across Function Boundaries: Why Single-Function Taint Analysis Fails
Every SAST scanner finds the obvious pattern: a tainted variable fed directly into an LLM call in the...
View lesson → + Playlist
From Regex to AST: Building Taint Tracking for AI Agent Code
Dev.to · Dockfix Labs 1w ago
From Regex to AST: Building Taint Tracking for AI Agent Code
How AgentGuard v0.5.0 traces data flow from user input to LLM sinks using Python AST analysis.
Read article → + Playlist
How to Hack an AI Agent (And How to Stop It)
Dev.to · Dockfix Labs 🤖 AI Agents & Automation ⚡ AI Lesson 1w ago
How to Hack an AI Agent (And How to Stop It)
7 real AI agent attack patterns with exploit code and fixes -- prompt injection, tool poisoning, data exfiltration, and more.
View lesson → + Playlist
900+ Downloads, 1 Star, 1 Comment: What I Learned Launching a Security Tool
Dev.to · Dockfix Labs 🔐 Cybersecurity ⚡ AI Lesson 1w ago
900+ Downloads, 1 Star, 1 Comment: What I Learned Launching a Security Tool
Two weeks of open-source security tooling: download numbers, what worked, what did not, and technical lessons.
View lesson → + Playlist