PexLens Blog
Insights & Research
Threat research, advisories and product news from PexLens.
AI & Agent Security, ResearchPrompt Assets Are Supply-Chain Assets: Securing System Prompts, Tool Instructions and Agent Playbooks
System prompts, MCP tool descriptions and agent playbooks shape what AI agents do. Learn how tool poisoning works, which patterns make prompt assets unsafe,…
Read article →
AI & Agent Security, ResearchYour AI Coding Assistant Is a Privileged Insider: Modeling Blast Radius Before an Incident
AI coding assistants read your code, hold your credentials and can reach your pipeline. Treat them as privileged insiders: work out what a compromised…
Read article →
AI & Agent Security, DevSecOps, Extension Security, ResearchExtension Drift: The Supply-Chain Risk Hiding Inside Routine IDE Updates
Extension drift turns trusted IDE updates into attacks. See what the Claude Code incident showed and how PexLens protects developers and teams.
Read article →See what is hiding in your dependencies
PexLens catches malicious packages and risky extensions before they reach your developers.