How to put guardrails around coding agents that write security fixes: Trail of Bits' patching-bugs and regression-hunt plugins, a THREAT_MODEL.md, live proof-of-concept gates and a three-arm proof.
Practical architectures, frameworks, and controls to secure AI systems in production.
How to put guardrails around coding agents that write security fixes: Trail of Bits' patching-bugs and regression-hunt plugins, a THREAT_MODEL.md, live proof-of-concept gates and a three-arm proof.
A practical defender's guide built on Unit 42's November 2026 findings: how to spot AI-driven red-team tooling like ARTEX by its behaviour, and which exposure and credential changes starve it.
Two NCSC blogs offer a five-dimension rubric for risky defensive automation and network and compute sandbox maturity levels. We combine them into one checklist; the mapping between them is ours, not the NCSC's.
Uber's Agentic AI Detection and Response system correlates LLM reasoning with MCP tool calls to catch prompt injection, credential leaks, and rogue agent behavior across thousands of production coding sessions.
Researchers from HKUST and NUS propose a tagging-and-filtering defense that asks LLMs to cite which instruction they are answering, cutting prompt injection success rates from over 80% to under 1% without any fine-tuning.