agentic-ai

AI Security Guardrails Are Failing Quietly, and Two New Studies Prove It

John Z Black Apr 6, 2026

AI Security #ai-security #claude-code #amazon-bedrock #guardrails #agentic-ai #prompt-injection

Claude Code's deny rules silently break after 50 subcommands and Bedrock's guardrails don't cover multi-agent flows by default, proving that AI safety tools work in demos but fail in production.

RSAC 2026 Day One: Every Vendor Went Agentic, the Government Went Missing

John Z Black Mar 24, 2026

Policy, Law & Governance #rsac-2026 #ai-security #agentic-ai #cisa #government-cybersecurity #google-cloud #microsoft #crowdstrike #wiz

RSAC 2026 opened with a wave of autonomous AI security launches from Google, Microsoft, CrowdStrike, and Wiz. Reportedly absent from the program: CISA, the FBI, and the NSA.

RSAC 2026 Opens Monday: Here's What the Cybersecurity Industry Will Be Talking About All Week

John Z Black Mar 22, 2026

Security Operations & Resilience #rsac #rsac2026 #agentic-ai #conference #microsoft #booz-allen #cyber-policy #ai-security

RSAC 2026 opens Monday at Moscone Center. Agentic AI, human manipulation, and post-breach resilience are the dominant themes -- here's what to watch and why this year feels different.

Agentic AI Just Had Its First Major Enterprise Data Breach — and the Attacker Was the AI

John Z Black Mar 22, 2026

AI Security #agentic-ai #mcp #owasp #meta #ai-security #prompt-injection #enterprise-security

A Meta AI agent followed its instructions and caused a major internal data leak. Combined with the new OWASP MCP Top 10, this is the clearest real-world picture yet of what agentic AI security failures actually look like.

AI Agents Have a Security Problem — and It's Not Science Fiction Anymore

John Z Black Mar 15, 2026

AI Security #ai-agents #prompt-injection #llm-security #agentic-ai #enterprise-ai #owasp-llm

AI agents aren't chatbots. They act, execute, and chain decisions on their own. And the security model for most deployments? Basically nonexistent.

Your AI Automation Platform Is a Backdoor: n8n RCE and a 4-Minute AI Browser Phishing Attack

John Z Black Mar 12, 2026

Vulnerabilities #n8n #ai-security #automation #prompt-injection #cve-2025-68613 #cisa #agentic-ai #perplexity

CISA flagged an actively-exploited RCE in n8n with 24,700 exposed instances. Researchers turned Perplexity's AI browser into a phishing tool in under four minutes. When software acts for you, it can be turned against you.