Tag:AI

OpenAI, Anthropic, Meta and the UK AI Security Institute have each now disclosed agents reaching systems they were never authorised to touch. Luke Potter revisits his original AI agent security analysis with the fuller evidence, and what it demands of containment design.

Stencilled figures scatter down a concrete stairwell, several breaking away from formation, symbolising AI agents moving outside their intended scope.

The OpenAI agents didn’t go rogue. They went out of scope, together.

OpenAI, Anthropic, Meta and the UK AI Security Institute have each now disclosed agents reaching systems they were never authorised…
Stencil silhouette of a child walking along a concrete wall beside a gap in a chain-link fence, symbolizing a gap in AI agent governance and containment boundaries

You can’t secure what you can’t see.

OpenAI's own agent breached Hugging Face's infrastructure without ever going rogue. It just stayed on-task and found the gaps in…
fallback image

When the API Lies – How RAID Discovered a Critical Privilege Escalation by Reading JavaScript

A privilege escalation vulnerability hid behind a broken endpoint and a misleading error message. Here's how RAID's agentic system decompiled…
Alt text "Stencil street art of a man in a suit, one hand pressed to his face, mouth open mid-scream, on a teal wall — symbolizing loss of control and panic in the face of a security breach.

The OpenAI agent didn’t “go rogue”. The containment failed. 

I’ve purposely held back from commenting on the OpenAI and Hugging Face incident.  The early coverage was predictably dramatic.  AI…
fallback image

How RAID found unauthenticated customer data in a retail GraphQL API

CovertSwarm's web testing agent identified a critical broken access control vulnerability in a retail subscription platform's GraphQL middleware. The platform…
CREST AI charter logo

CovertSwarm is a founding signatory of the CREST AI Charter

CovertSwarm has become a founding signatory of the CREST AI Charter, endorsing nine principles for responsible AI use in cybersecurity.
Frontier AI models and offensive security - Luke Potter CovertSwarm

Frontier AI models are exciting.

CovertSwarm COO Luke Potter on why frontier AI is genuinely exciting, why most of the conversation is asking the wrong…
A lone figure walks away down a dark, empty street at night, unseen and undetected.

AI Sharpens the Question. It Doesn’t Change the Answer.

The cyber security industry has spent decades selling findings instead of answers. AI tools like Mythos make the problem faster…
Mythos ai zero day discovery

Mythos found a $20,000 bug. It won’t tell you who’s already inside. 

Anthropic's Mythos has dominated the security conversation this week. But the debate about whether it's overhyped is the wrong argument.…