Ai-Security

Comprehensive AI / LLM Security Guide 🆕 Updated September 12, 2026 — added the LiteLLM gateway chain (CVE-2026-59821/59822): default keys to RCE to IAM theft, and why the SSRF in it will never get a CVE. A practitioner’s reference for securing Large Language Model and agentic AI systems — attack surface, exploitation techniques, real-world CVE chains, payloads, and layered detection/prevention. Draws on published research from OWASP, NVIDIA AI Red Team, Unit 42, Lakera/Check Point, NCSC, CrowdStrike/Pangea, Equixly, Anthropic, OpenAI, Microsoft MSRC, Google, AWS, MITRE ATLAS, Red Hat, Pillar Security, JFrog, AuthZed, and Trend Micro. ...

If you want the short answer to “how should I limit an AI coding agent’s permissions?”, it’s this: give the agent its own identity instead of yours, hand it short-lived credentials scoped to the one task in front of it, make read-only the default, keep production credentials somewhere it physically can’t reach, and require a human to approve anything destructive. That’s least privilege, the same rule we’ve applied to service accounts for twenty years. We just forgot to apply it to the newest and most enthusiastic service account on the team. ...