Agents
Showing 21–40 of 65 posts
- Security & Risk
Trail of Bits’ coop gives coding agents their own working environment
coop runs Claude Code and Codex in disposable virtual machines, with project sync and controls for connecting files, credentials and local models.
- Security & Risk
AI agents compressed a conventional intrusion into ten hours
Unit 42 investigated an intrusion run through AI agents in under ten hours. Its own report says no novel zero-day was needed, a human made the decisions.
- Security & Risk
OpenAI Wants Your Trust, Your Calendar and Your Card
OpenAI paused frontier training and wound down its side projects. The product it is refocusing on asks for your calendar, your finances and your card.
- Agents & Tooling
Runway's Solaris generates app interfaces frame by frame, with no code
Runway's first Interface World Model generates a UI frame by frame with no code underneath. Accessibility is on its own list of unsolved problems.
- Security & Risk
Anthropic says it had one layer of defence where it needed several
Anthropic's post-incident write-up admits it relied on a single layer of defence where it needed several. The independent METR review is still to come.
- Security & Risk
An agent's tool list shows what you wired into it
A ChatGPT Work session published its tool and skill inventory as a public website. The category names show which integrations that session had been given.
- Agents & Tooling
The magic in agent interfaces still needs an off switch
Two instincts about talking to agents: make the explicit path reliable, or design the naming away.
- Agents & Tooling
Cloudflare can now see some MCP traffic, and the gap is the point
Cloudflare is clear that its absence proves nothing, which makes this a network inventory signal rather than a census of agent activity.
- Security & Risk
OpenAI's agents were persuaded past their own refusal
An agent recorded an ethical objection to running code against Hugging Face, then complied when another agent posted a deadline and a GO.
- Security & Risk
Tailscale Aperture treats agent access as a change-control problem
Aperture is generally available. An agent can start infrastructure work, a person still approves every new machine on the tailnet.
- Security & Risk
A webcam's recording light is only useful if its firmware is protected
Chaz Schlarp used Claude Opus 5 to reverse-engineer five desk peripherals in about 13 hours, including a webcam whose recording LED he could switch off.
- Security & Risk
The robot arm will obey the limits you remembered to write down
Anthropic's Model Hardware Standard lets agents drive lab instruments over MCP, and enforces safety limits below the agent.
- Agents & Tooling
WebMCP could make browser agents less clumsy. It also makes permission design unavoidable.
A proposed browser API gives AI agents structured access to specific tasks on a website, instead of leaving them to guess at the UI.
- Agents & Tooling
One Foot on the Brake, One on the Gas
OpenAI paused two weeks of its own training over cyber risk, then shipped a browser agent that signs into your accounts.
- Agents & Tooling
What a Climbing Harness Tells You About AI Agents
The word "harness" has been used in AI tooling for months without a clear definition. Earendil finally gives one.
- Security & Risk
Agents Don't Believe in "No-Win" Scenarios
An OpenAI evaluation agent broke into Hugging Face to steal a benchmark's answers — by turning the systems around it into an escape route.
- Agents & Tooling
Cloudflare built the agent cloud in a week — and kept the human at the controls
Cloudflare's Agents Week shipped a full stack for AI agents: a runtime, an identity, a wallet, a route onto the web, and the security around it.
- Security & Risk
OpenAI Published Its Homework on Exactly the Question I Keep Asking
Codex Security is worth taking seriously precisely because it reads as an admission. It also leaves the harder half of the problem completely uncovered.
- Security & Risk
The Text Your Agent Reads Isn't the Text You See
Your AI can read instructions that are invisible to you. New security research shows how hidden codes get smuggled into the tools your assistant uses.
- Security & Risk
Agent Security Just Got Real CVEs
Prompt injection chains to RCE in CrewAI. 22-second attacker breakout. Human-in-the-loop is no longer a security control.
