TL;DR: Separating sensitive code, sandboxing agent execution and filtering outbound prompts are the controls that make LLM-assisted development workable, according to Guardsquare. AI-assisted workflows need enforceable boundaries so IP, PII and credentials do not leave the developer environment.
Editorial analysis by NHI Mgmt Group, based on content published by Guardsquare: “Safeguarding LLM-Assisted Dev at Guardsquare”.
Key questions
Q: Why do LLM-assisted coding tools create security risk even when developers are careful?
A: Because the client can read more of the workstation and repository ecosystem than the developer intends, including caches, copied files and hidden paths.
Q: What are the signs that LLM-assisted development is outpacing review capacity?
A: Look for oversized pull requests, longer review cycles, repeated rework and a growing queue of changes that were generated faster than humans can validate them.
Q: How should security teams reduce the risk of insecure code from LLM-assisted development?
A: Security teams should treat LLM output as a starting point, not a trusted implementation.
Practitioner guidance
- Separate sensitive repositories from LLM-enabled work Move protected code, confidential notes and other high-risk assets into repositories where model assistance is prohibited, and account for duplicate copies in Git objects, caches and package stores.
- Wrap the client in a deny-first sandbox Use container-based isolation or host-level policy controls to restrict filesystem, process and network access to the minimum needed for the task.
- Inspect every outbound prompt through a gateway Route model traffic through an approved gateway and guardrail layer that can block sensitive content before it leaves the developer environment.
Bottom line: LLM-assisted development changes the security problem from model quality alone to control of sensitive code, prompts and execution paths.
Glossary terms: LLM-assisted development, Sandboxing Technology, Prompt boundary, Review Funnel
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
LLM-assisted development is now a secrets-governance problem, not just a coding-productivity decision. The article shows that the real control question is whether sensitive code, copies, caches and prompts stay inside a governed boundary. For identity and access practitioners, that makes the developer toolchain part of the same policy surface as credentials and privileged workflows. Practitioner conclusion: treat AI-assisted coding as an access boundary that must be designed, not assumed.
A few things that frame the scale:
- AI-related credential leaks surged 81.5% year-over-year in 2025, with the surrounding AI infrastructure leaking 5x faster than core LLM providers, according to the State of Secrets Sprawl 2026.
A question worth separating out:
Q: Should organisations trust model evaluators and built-in agent safeguards?
A: No, not as the primary control. If the first model cannot be trusted with unrestricted access, a second model used to approve its actions is not a sufficient substitute for runtime isolation. Organisations should prefer enforceable sandbox policy, explicit allowlists and human review for sensitive tasks, especially where code, data or credentials are involved.
👉 Read our full editorial: LLM-assisted development needs sandboxing, gateways and stricter review