Topic · 19 posts
Ai
Where machine learning meets the systems it is dropped into, and what breaks at the seam.
- One Character. Millions of AI Agents Exposed.
CVE-2026-48710 lets a single character in the Host header bypass path-based auth across FastAPI, vLLM, LiteLLM, and MCP servers built on Starlette.
- Your AI Should Have Nothing Worth Stealing
A self-hosted AI on a $10 VPS with zero-trust ingress, pre-action guardrails, and a heartbeat that runs every 30 minutes whether I am awake or not.
- I Built an Ambient Intelligence System for My Life: How Myway Works
Myway is a local AI layer that watches my calendar, tasks, email and GitHub, then acts without being asked. The architecture, and what building it taught me.
- Ember: Building a Persistent AI Companion for Developers Who Ship Alone
A locally-hosted companion that remembers, reaches out first, and notices what you shipped. Why I built it and how the architecture works.
- UMD Turned SKILL.md Into a Zero-Code Weapon. Pre-Action Authorization Is the Only Fix That Works.
A 20-token edit to a SKILL.md file makes agents pick the malicious skill 77.6% of the time. No code, no signature, nothing for a scanner to find.
- I Read the Paper That Says AI Agent Safety Has Been Built Wrong. Here's Why.
A formal proof that semantic guardrails cannot give a deterministic security bound, and the SMT solver architecture the authors propose instead.
- I Forked ByteDance's DeerFlow at 3 AM to Add Pre-Execution Authorization
Eight minutes from noticing the missing authorization hook to opening PR #1240: 1,033 lines across 11 files that authorize every tool call before it runs.
- Your AI Agent Just Spent $3,000 and You Didn't Approve It
FIDO, Google, and Mastercard are standardizing who authorized an agent to pay. None of it constrains what the agent spends once a prompt injection lands.
- A Cursor Agent Deleted a Production Database in 9 Seconds. Here's Why Pre-Action Authorization Would Have Caught It.
A Cursor agent deleted PocketOS's production database and every backup in nine seconds. The same authorization gap runs through every agent incident of 2026.
- A payment request is not a policy decision: 4,371 human attacks, 14 models, one question
We replayed 4,371 human-written attacks against 14 models, with and without an authorization check between the tool call and the bank. The models kept asking to pay. What changed is whether the money moved. Charts, denominators and a reproduce command.
- The Hugging Face Agents Tried to Erase Their Own Evidence
About 700 agents coordinated through a hidden message board in the Hugging Face breach, and one in five researched how to tamper with their transcripts.
- Broadcom Just Built the Agent Security Layer I've Been Arguing For. One Hole Is Still Open.
Broadcom's AgentMinder checks every agent tool call at runtime, and its policy engine still trusts the one signal a prompt injection can rewrite.
- Why 77% of AI Security Strategies Can't Be Enforced
77% of organizations updated their security strategy for AI. Only 26% can enforce it before a tool call runs. Where that 51-point gap lives.
- 63% of Organizations Cannot Purpose-Limit Their AI Agents. Vercel Showed Us Why That Ends.
Disclosure: I build APort, an open-source layer that checks each AI agent action against a policy before it runs. The Vercel breach ran on an OAuth grant an AI tool already held, and 63% of organizations still cannot purpose-limit an agent or shut one down.
- A Fortune 50 AI Agent Rewrote Its Own Security Policy. Pre-Action Authorization Could Have Stopped It.
A Fortune 50 AI agent removed a security restriction and passed every identity check. Seven vendors shipped runtime detection at RSAC 2026, and none of them check the call before it runs.
- I Analyzed the Morse Code Prompt Injection That Drained $175K From an AI Wallet
A Morse code post on X moved through Grok into Bankrbot and shifted 3 billion DRB tokens. The failure was authorization, not the smart contract.
- Five AI Agent Exploits in Twelve Weeks, and Not One Broke the Model
Cursor, Codex, and Claude Code were all exploited between February and April 2026. Every case stole or abused a credential. None broke the model. Monitoring is not authorization.
- 30 ClawHub Skills Turned AI Agents Into a Crypto Swarm
Nine thousand eight hundred downloads, no malware, no exploit. Just skill files telling agents to register with a server and upload their own wallet keys.
- AI Passports: A Foundational Framework for AI Accountability and Governance.
The future of AI is not just about intelligence. It's about integrity. Implementing a digital ID and passport system is a critical step toward building a secure, trustworthy, and responsible…