Security Insights
Latest threat analysis, industry news, and security best practices from our expert team.
Forensic Reconstruction of AI Coding Agents: Detection, Artifact Locations, and IR Playbook for Claude Code, Codex, Gemini CLI, and OpenCode
Introduction A quiet shift has occurred in enterprise endpoints over the last 18 months: developers and engineers are running autonomous and...
Anthropic's Free Claude Code Cloud Sessions: A Defender's Guide to Shadow AI Risk, Detection, and Governance
Introduction Anthropic has opened Claude Code cloud sessions to general users — no research preview signup required — and is sweetening the ...
Plugin4Shell Supply-Chain Flaw in Claude Code, Codex, and Copilot: Detection and Remediation Guide
Introduction Air Security disclosed a supply-chain vulnerability class this week that should be on every CISO's radar — especially organizat...
Self-Generated Prompt Injections in AI Compaction Summaries: Defending Claude Code and Coding Agents Against Persistence Attacks
A New Persistence Layer: When the AI Writes Its Own Malware Instructions Simon Willison's September 2026 write-up on self-generated prompt i...
Malicious .git Configs Hijack Claude Code, Codex, Cursor AI Agents — Detection and Hardening Guide
Introduction Manifold Security has disclosed a cluster of eight vulnerabilities spanning seven command-line AI coding agents — including Ant...
Securing Claude Code: Detection, Compliance API Monitoring, and Identity Governance for AI Coding Agents
Introduction AI coding assistants have crossed a line that security teams can no longer ignore. Claude Code is not a chatbot in a browser ta...
Anthropic Cuts Claude Code Weekly Limits by 17%: What Security and Platform Teams Need to Do Now
Introduction Anthropic has announced a permanent change to Claude Code's standard weekly usage limits — a 25% increase to the baseline limit...
Claude Code Opus 5 Auto Mode Prompt Injection Bypass: Detection and Hardening Guide for AI Coding Agents
Overview Johann Rehberger — one of the most credible prompt injection researchers working today — has demonstrated a bypass of Anthropic's C...
Prompt Injection Hijacks Claude Code Opus 5 Auto Mode — Detection and Hardening Guide
Researchers have demonstrated that a simple webpage summarization request can hijack Claude Code running Opus 5 in Auto Mode — the now-defau...