Topic starter
10/06/2026 11:23 pm
TL;DR: Claude Code agents can already read files, run commands, and chain tool calls, but local hooks alone leave no central audit trail or enforceable policy layer, according to Cerbos. The real governance gap is assumption collapse: access review and IAM controls were built for stable identities, not per-tool decisions made at runtime by agentic workflows.
Editorial analysis by NHI Mgmt Group, based on content published by Cerbos: “Governing AI coding agents with Cerbos Synapse”.
Key questions
Q: Where does Claude Code governance fail when hooks are only local?
A: It fails at consistency and enforceability.
Q: Why do AI coding agents need central audit trails for tool calls?
A: Because the risk is in the action stream, not just the login.
Q: What do security teams get wrong about Claude Code hooks?
A: They often treat hooks as if they are governance by themselves.
Practitioner guidance
- Deploy central policy enforcement for agent tool calls Route Claude Code tool events through a centrally managed policy decision point so every read, write, and shell invocation is evaluated against the same rules.
- Move hooks out of local developer config Use server-managed settings or managed device configuration so hook enforcement cannot be removed, redirected, or skipped by individual users.
- Log every allow, deny, and no-match event Capture decision logs with principal identity, roles, resource attributes, and the tool context so auditors can reconstruct what the agent did.
Bottom line: Claude Code agents expand the governance surface from user login to per-tool authorisation decisions, which local hooks alone cannot control consistently.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
This topic was modified 5 days ago by NHI Mgmt Group
12/06/2026 5:20 am
Claude Code governance breaks when runtime policy is left local: the assumption behind access review is that the identity and its permissions are stable long enough to be reviewed. That assumption fails when an AI agent makes tool-use decisions at runtime and the only control is a per-developer hook config. The implication is that the governance object is no longer the developer endpoint but the centrally enforced decision boundary.
A few things that frame the scale:
- Claude Code-assisted commits leaked secrets at a rate of 3.2%, more than double the human-only baseline of 1.5%, with peaks reaching 31 secrets per 1,000 commits in August 2025, according to the State of Secrets Sprawl 2026.
- 7% of security leaders admit they do not know how often their AI systems are making autonomous changes to infrastructure, according to the 2026 Infrastructure Identity Survey.
A question worth separating out:
Q: How should teams govern AI agents that can reach APIs, events, and memory?
A: Teams should govern those agents as runtime identities, not as isolated integrations. That means enforcing policy at execution time, logging every tool and data access, and binding actions back to a clear initiating workflow or identity. If the control plane cannot show who acted, what they reached, and why, the programme does not have usable governance.
👉 Read our full editorial: Policy controls for Claude Code agents need central enforcement
This post was modified 5 days ago by NHI Mgmt Group