What our agents found, and how they found it.

AI agent swarm attacks: what the Hugging Face breach shows about your external attack surface

About 700 AI agents broke out of an evaluation and breached Hugging Face. Every vulnerability class they used was old. The first door they walked through was already open to the internet.

Nov 202612 minRead

External penetration testing in the age of AI attack swarms: a 2026 guide

External penetration testing isn't dead. The assumption behind it is.

Time to exploit in 2026: how fast vulnerabilities get exploited

Mandiant's average went from 63 days to minus seven. We checked every vulnerability CISA confirmed as exploited this year against its publication date. Half were confirmed within four days.

Nov 202610 minRead

Vulnerable vs exploitable: why 4,000 findings aren't 4,000 risks

A vulnerability tells you something is wrong with the software. Exploitability tells you what an attacker can do about it, from where they actually stand. Only the second one should set your priorities.

Claude Mythos for defenders: what changes when finding exploits costs nothing

Mythos isn't public, and some of the hype is overstated. What's real is the price drop: known bugs become working exploits in hours, and small flaws get chained. The gap is knowing which ones are exploitable on your perimeter.

Nov 202612 minRead

AI pentesting in 2026: what autonomous agents find, and what still needs an operator

Every vendor has an agent now, and so do the attackers. The difference is what happens between "the agent found something" and "this reaches your team": who checked it, how it was proven, and where somebody decided to stop.

Supply chain attacks in 2026: Trivy → LiteLLM → axios, seen from the outside

Trivy, LiteLLM and axios fell within two weeks, and none of them through their code. Every link in the chain ran on a credential that had leaked and was still valid.

Nov 202612 minRead

AI agent security: how an attacker sees the AI agents in your company

Most of the conversation is about agents going rogue. From the offensive side, what breaks in is access nobody mapped. Five attack paths we walked in 2026, and what to do this week.

Red teaming in the AI era: what it is, why it's different, and what your board should require

What red teaming is, how AI changes it, and what governance your board should require.

Nov 202611 min readRead

How much does a penetration test cost, and how do you choose a vendor?

Published vendor prices, seven cost drivers, six questions to ask before signing, and why annual testing leaves gaps.

Nov 202612 min readRead

Attack surface management vs. continuous external red teaming: exposure is not exploitability

ASM finds what is exposed. Red teaming proves what is exploitable. A side-by-side comparison with real data.

Nov 202611 min readRead

Shadow AI is the new shadow IT: why it's worse, and what to do about it

Shadow AI copies code, credentials and logic outside the organization at scale. Here is what the numbers say and what to do about it.

Nov 202611 min readRead

Clay security nodes surrounding exposed source code

Shadow Code: an AI built the backdoor. Another AI found it.

From one company name to a critical stored SQL injection inside code nobody knew was public.

Jun 202612 minRead

Clay blocks tracing a CI supply-chain attack path

One pull request to own the supply chain

How an untrusted pull request reached production secrets and package-publishing rights.

May 202611 minRead

Cutaway clay model of an exposed monitoring system

No login required: a Grafana that hands out database credentials

A public dashboard became an unauthenticated proxy into its production database.

May 202610 minRead

One sign-up form away: anonymous to full recon

Four weaknesses chained from open registration to metadata theft and proprietary model exposure.

May 202610 minRead

Clay package blocks sharing one dependency name across two registries