6 min read
Buy the Control Plane. Then Prove It Works.
Agent control is turning into a product you can buy. Open or closed, you didn't write it, so what it does in your environment is the only proof you'll get.
Tagged: safe-autonomy
26 posts tagged with “safe-autonomy”
6 min read
A Record of Approval Is Not Approval
Darktrace rewrote the saved conversations of four coding agents and got them to attack a network. The lesson isn't about signatures. It's about where your agent's permission comes from.
7 min read
I Attacked My Own AI Agents — What Held, What Didn't
Three pieces of research showed how to hijack AI coding agents. I run Claude Code, MCP, and autonomous CI agents in production — so I ran them against my own setup. Here's what held, what didn't, and what I changed.
6 min read
The 12-Factor Agent's Missing Factor Is Security
The 12-factor-agents spec never says security out loud — yet owning your context window is DLP, a structured tool schema is your authorization point, and a human-contact tool call is your approval gate. Reliability and security are the same seams read twice.
5 min read
Skill Was Never the Threat — Scaffolding Is
Everyone is auditing the model. The real attack surface is the harness you wrap around it — the scaffolding that wires tools, memory, and control flow into an agent that can actually act.
7 min read
The 97% Number: What Happened When We Automated Security Triage
We automated security alert triage to a 97% noise-reduction rate — then a suppression rule went stale and nearly let a production vulnerability through unnoticed.
7 min read
Why We Failed Our Agent-Readiness Audit on Purpose
An automated audit gave us nine recommendations for being 'agent-ready.' We shipped three and deliberately failed the other six — because a security firm's agent-readiness is measured by signal honesty, not checkbox coverage.
9 min read
Project Glasswing: AI Finds Zero-Days Faster Than Humans Can Patch Them
Anthropic's Project Glasswing deployed Claude Mythos Preview to autonomously discover thousands of zero-days with a 72.4% exploit success rate. Less than 1% of findings have been patched. The bottleneck is no longer discovery — it's everything that comes after.
6 min read
AI Executes. Humans Own It.
The execution case and the accountability case are both right. The interesting question is what happens when you put them together.
5 min read
Your Compliance Assessment Does Not Cover AI Agents
NIST RA-5, ISO 27001 9.2, DORA, FedRAMP 20x — four major compliance frameworks share the same blind spot: none of them account for AI agents in your environment. Here is what that means and what to do about it.
10 min read
Amazon Kiro Deleted Production. Here's What Every Engineering Leader Should Learn.
Amazon mandated 80% adoption of its AI coding agent Kiro. Then Kiro deleted a production environment, caused a 13-hour AWS outage, and kicked off a chain of incidents that cost millions of orders. The failure wasn't the AI — it was deploying autonomy before safety infrastructure existed.
8 min read
Your Agent's Real Attack Surface Isn't Its Prompt
Everyone optimizes the token window. Almost nobody manages the environment. Active context is what your agent thinks about. Latent context is what your agent can reach. The blast radius of a compromised agent is determined by the latter.
9 min read
Hardening Claude Code for Production: What CVE-2026-21852 Doesn't Tell You
The upstream fix for CVE-2026-21852 protects interactive users. It does not protect headless mode. We tested this against our own production deployment and watched 18 API requests redirect to an attacker-controlled server in 30 seconds. Here is what we found and how to fix it.
15 min read
Identity Is the Missing Layer for AI Agents
Your AI agents inherit your permissions, your credentials, and your blast radius. NIST just proposed a fix — and the public comment window closes April 2. Here's why identity governance is the layer most agent architectures are missing.
14 min read
Your Token Budget Is a Security Control
Most teams treat token spend limits as cost management. They are blast radius containment. An autonomous agent with no spending ceiling is not a productivity tool — it is an uncontrolled liability.
10 min read
The AppSec Acceleration: Why Your Security Tools Can't See Agent Vulnerabilities
Traditional SAST, DAST, and SCA tools were built for request-response architectures. Agent-first systems have vulnerability classes these tools were never designed to detect — and independent research just confirmed it.
15 min read
Specification as Attack Surface: Why Ambiguity Is a Vulnerability in Agent-First Architectures
Ambiguous specifications aren't just a project management problem anymore. In agent-first architectures, every gap in a spec is a potential security boundary violation — and the agent won't tell you it's guessing.
11 min read
How We Work: Automation Engagements
What an automation engagement with Atypical Tech actually looks like — from discovery through validation. No paved cow paths, no automation theater, no surprises.
11 min read
The OWASP Top 10 for Agentic AI Is Here — What It Means for Your Deployment
OWASP released its first Top 10 for Agentic Applications. Here's what each risk means, why traditional AppSec frameworks fall short, and how to start securing your AI agents today.
5 min read
Palantirization and Safe Autonomy: The Same Bet
The trap a16z identified for FDE-model startups is identical to the trap facing AI agent deployments.
7 min read
Safe Autonomy for AppSec: Where AI Agents Actually Help
How the Safe Autonomy framework applies to vulnerability triage, alert correlation, compliance evidence, and security testing. AI agents can multiply your security team—if you build the right guardrails.
5 min read
Accountability Stays Human: The Accountability Proxy
Autonomy concentrates responsibility. Here’s why every agent needs a named human owner and runtime governance controls.
5 min read
Interfaces Define Capability and Risk
The integration surface isn’t an implementation detail — it’s the boundary that determines what autonomy can safely do.
5 min read
Structure Beats Prompts: ROBOT in the Wild
Same model, different outcomes: why supervision, specialization, triage, and long-horizon context management matter more than prompt cleverness.
5 min read
Reveal Is Not Optional: The Trust Layer Autonomy Can’t Skip
Why “show your work” is a control surface, not a UX detail — and how evidence packets, confidence bands, and verification gates prevent the false confidence tax.
5 min read
Safe Autonomy in the Real World: 4 Lessons from a Live Humans-vs-Agents Trial
A case-study-driven series on what changes when agents operate in messy reality: reveal, structure, interfaces, and human accountability.