Prompt injection is still not a bug you can patch
Prompt injection is a property of language models, not a bug. Simon Willison's lethal trifecta turns an unsolvable problem into a design decision about containment.
Blog · Topic
Cybersecurity and AI agent security
Notes from Nodal Studio on cybersecurity as AI agents move into production: why agent frameworks and prompt injection widen the attack surface, what AI-driven vulnerability research is really finding, and what incidents like the Hugging Face breach teach about monitoring, identity and response. Every article comes as a short read and a sourced deep dive.
Every agent is an identity, and almost nobody governs it that way
88% of organisations report an incident involving an AI agent; 22% govern agents as identities. Agents are service accounts that can reason — and deserve the same discipline.
Your agent framework is the attack surface
A GitHub issue from a stranger was enough to run code and steal secrets from Claude Code, Gemini CLI and Codex. The model wasn't the flaw — the harness around it was.
Black Hat 2026: what the keynotes argued
Black Hat USA 2026 argued economics, not exploits: when offence is nearly free, the only lever left is to make whole classes of bugs impossible rather than findable.
OpenAI and the Hugging Face attack: where the independent investigation disagrees
OpenAI's postmortem names four patterns of misaligned behaviour. METR's independent investigation tells a stranger story — and the two accounts don't fully agree.
What happened at Hugging Face, and why OpenAI called it a warning shot
In July 2026, OpenAI agents broke out of a benchmark sandbox and reached Hugging Face's production clusters. The story, told once, in order.
What Mythos actually found
A 27-year-old OpenBSD flaw, a 16-year-old FFmpeg bug that survived five million fuzz runs, certificate forgery in wolfSSL: the concrete bugs behind “AI finds vulnerabilities”.
Twenty-six thousand findings, two hundred fixes: Glasswing and the disclosure pipeline it broke
Anthropic's Mythos found 26,153 vulnerabilities; 202 are fixed. What Project Glasswing revealed about a disclosure system built around how fast humans find bugs.