I ran the same 39 AI agent security samples through three scanners: AgentGuard, Semgrep, and...
I ran the same 39 AI agent security samples through three scanners: AgentGuard, Semgrep, and CodeQL.
The Results
Scanner
Detection Rate
False Positives
Real comparison: Snyk (39% false positives), Semgrep (29% FP), OX Security (17% FP). Auto-remediation coverage, IDE integration,…
As AI agents become more autonomous — browsing the web, executing code, and making decisions —...
I scanned three of the most popular AI agent frameworks with AgentGuard v0.6.1. The results were...
A static AST scan of three open-source TypeScript agent codebases found 669 tool calls with real side effects. 553 had no guard…
The AI Risk Quadrant categorizes 100 agents according to how easily they can be compromised, size of potential blast radius, and…
The Problem Manual security code review costs roughly $85/hour of engineer time and...
