Coding agents: Cursor gives them computer use, Claude Code patches its sandbox
On the same day, two flagship tools show the two sides of development agents: more capabilities on one hand, more guardrails on the other.
Programming agents no longer just write code in an editor. Two recent announcements show how far they now go, and why security is becoming central.
Cursor: the agent can use a computer
On October 23, Cursor published documentation for Computer Use in its self-hosted cloud agents. The idea: the agent is no longer limited to files and the terminal; it can also drive a graphical environment, for example to check how an interface renders. The fact that the feature is documented in the “self-hosted” section is notable: the company keeps control of the machine on which the agent acts.
Claude Code: more than ten sandbox flaws fixed
On the Claude Code side, the changelog for versions 2.1.309 and 2.1.310 reports fixes for more than ten bypasses of the sandbox and permission system. In other words, there were more than ten ways to get outside the perimeter the agent was allowed to work in.
Why this is one story
The more capabilities an agent has (running commands, clicking, browsing), the more the quality of its isolation matters. A bypassed sandbox on an agent that drives an entire computer has far heavier consequences than on a simple autocomplete assistant.
Our take
For teams: update Claude Code without delay, and keep computer-use features to dedicated machines with no access to production secrets. Agents are gaining power faster than their guardrails.
Sources
- Cursor — Computer Use documentation (self-hosted cloud agents) Primary source
- Claude Code — official changelog Primary source
A primary source comes directly from the company, lab or organization concerned. A secondary source reports the information without being its author: we flag it as such. Spotted an error? See our corrections policy.