https://newsletter.aminrj.com/ 2026-02-20 https://newsletter.aminrj.com/authors 2026-04-30 https://newsletter.aminrj.com/authors/amine-raji 2026-03-09 https://newsletter.aminrj.com/p/ai-sec-intel-9-eight-agent-exploits-in-q1-200k-vulnerable-mcp-servers-and-anthropic-won-t-fix-the-pr-2f8b 2026-04-29 AI Security Intelligence en 2026-04-29T19:26:52Z [AI Sec Intel] #10 — MCP servers trust every caller by default. Here's the checklist that closes the gap. https://newsletter.aminrj.com/p/ai-sec-intel-9-eight-agent-exploits-in-q1-200k-vulnerable-mcp-servers-and-anthropic-won-t-fix-the-pr 2026-04-21 https://newsletter.aminrj.com/p/ai-sec-intel-8-closed-agent-harness-threat-model-blind-spot 2026-04-14 https://newsletter.aminrj.com/p/ai-sec-intel-7-97-expect-an-ai-agent-breach-this-year 2026-04-08 https://newsletter.aminrj.com/p/ai-sec-intel-6-trivy-compromised-litellm-backdoored-your-ci-pipeline-is-the-new-attack-surface 2026-03-31 https://newsletter.aminrj.com/p/ai-sec-intel-5-28-out-of-30-agent-projects-zero-per-agent-identity-zero-revocation 2026-03-24 https://newsletter.aminrj.com/p/ai-security-intelligence-4-knowledge-base-poisoning-95-success-rate-one-defense-layer-most-teams-are 2026-03-17 https://newsletter.aminrj.com/p/ai-security-intelligence-3-i-red-teamed-my-own-agent-stack-pleasefix-hijacks-browsers-through-calend 2026-03-09 https://newsletter.aminrj.com/p/ai-security-intelligence-2-claude-code-supply-chain-rce-ai-powered-fortigate-blitz-infostealers-now 2026-03-09 https://newsletter.aminrj.com/p/ai-security-intelligence-1-dockerdash-mcp-takeover-vllm-cvss-9-8-rce-cisco-state-of-ai-security-2026 2026-03-09