Claude Code security: are your controls keeping up with agent risk?

TL;DR: Claude Code’s official settings provide a useful floor, but local admin rights, multiple coding agents and harness-level bypasses leave enterprise deployments exposed, according to Adversa AI; Anthropic’s own tests show auto mode misses 17% of risky actions and users approve 93% of prompts. The real control problem is that governance assumptions about stable human review and single-surface enforcement do not hold once agents can work around them.

Editorial analysis by NHI Mgmt Group, based on content published by Adversa AI: “Is Claude Code safe for the enterprise? What the official settings cover, and what they don't”.

By the numbers:

• Users approve 93% of permission prompts anyway.

Key questions

Q: What breaks when coding agents run on developer laptops with local admin rights?

A: Managed policies become editable instead of enforceable, so the agent can inherit unsafe reach from the host.

Q: Why do coding agents increase secret exposure risk even when prompt approvals exist?

A: Because approvals usually judge one action at a time, while attacks exploit the chain between actions.

Q: How do security teams know if coding agent monitoring is actually working?

A: Monitoring is working when it can correlate session behavior, file access, tool use, and network attempts into a single investigative trail.

Practitioner guidance

• Lock down developer endpoints Remove local admin rights from machines that run coding agents, because managed settings are only durable when the host cannot rewrite them.
• Separate agent identities from developer credentials Issue short-lived, task-scoped credentials to the agent instead of letting it inherit SSH keys, cloud tokens and registry access from the user session.
• Default to denied egress Force all agent network traffic through a proxy or allowlist so a permitted command cannot become an exfiltration route to an unknown destination.

Bottom line: Claude Code security depends on the surrounding endpoint, harness and policy model more than the model layer itself.

Explore further

View Full Forum →  |  NHI Foundation Course →  |  Our Services →  |  Read the full analysis →