Topic starter
25/10/2026 11:10 am
TL;DR: Claude Code, Claude Code in the cloud and Cowork share the same build but diverge so sharply in plugins, hooks, settings, updates and status reporting that administrators must govern them as three separate platforms, according to Manifold Security research. Treating them as one control plane leaves configuration, enforcement and coverage gaps that clients may also misreport.
Editorial analysis by NHI Mgmt Group, based on content published by Manifold Security: “One vendor, three platforms: governing Claude Code and Cowork”.
Key questions
Q: Where does governance fail when one agent runs across multiple surfaces?
A: Governance fails when teams assume a single control model reaches every runtime.
Q: Why should security teams distrust client-reported plugin and hook status?
A: Because the client can report availability, disablement or loading in ways that do not match actual runtime behaviour.
Q: What are the best practices for governing AI coding agents across desktops and sandboxes?
A: Treat each execution surface as its own platform, map which controls it actually accepts, and test behaviour rather than assuming documentation is accurate.
Practitioner guidance
- Document each runtime surface separately Create a control inventory for terminal, hosted cloud and Cowork, then map which policy, plugin and hook mechanisms each one actually honours.
- Validate enforcement from outside the client Use external checks to confirm plugin loading, hook execution and configuration persistence instead of relying on client status output.
- Separate delivery from configuration governance Track plugin distribution, managed settings and storage location as distinct controls, because the article shows they do not converge naturally.
Bottom line: The article shows that one agent brand can conceal multiple administrative surfaces with different control behaviour.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →