TL;DR: AI coding assistants can make drafting feel faster while adding review and governance work before release, Cerbos found. Production code still needs tighter merge gates and scrutiny for credential handling when AI-generated output expands privilege paths and secrets exposure.
Editorial analysis by NHI Mgmt Group, based on content published by Cerbos: “The productivity paradox of AI coding assistants”.
By the numbers:
- AI-generated code introduced 322% more privilege escalation paths and 153% more design flaws than human-written code, according to Apiiro research cited by Cerbos.
Key questions
Q: Why do AI coding assistants create security debt even when code compiles?
A: Because compilation only proves syntax, not safety.
Q: What breaks when AI-generated changes are reviewed only at merge time?
A: Merge-time review fails because AI-driven pipelines can create code, dependencies, workflows, and infrastructure in one step.
Q: How should security teams govern AI coding assistants that can execute commands?
A: Treat them as delegated non-human identities with bounded execution authority.
Practitioner guidance
- Define approved AI coding use cases Limit assistant use to MVPs, experiments, boilerplate, and low-risk scaffolding where review burden is manageable and failures are easy to detect.
- Scan for secret exposure in prompts and output Treat pasted API keys, tokens, and config snippets as potential disclosure events.
- Tighten merge gates on assistant-generated code Require security review for changes that add privilege paths, authentication logic, or external integrations.
Bottom line: AI coding assistants can make drafting feel faster while increasing the amount of review, cleanup, and governance work needed before release.
Glossary terms: AI coding assistant, Privilege Escalation, Secrets Exposure, Production Readiness Gate
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Productivity is the wrong unit of control when AI coding assistants are in the delivery chain. Cerbos’ evidence shows that apparent speed can coexist with slower senior developers, more review work, and worse security outcomes. That means the governance problem is not tool adoption, but whether organisations are measuring the right end point: production-ready change, not prompt throughput.
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.
A question worth separating out:
Q: Should organisations compare AI coding assistants with human-only development for sensitive systems?
A: Yes, but the comparison should focus on change quality, review burden, and secret exposure rather than raw output speed. For sensitive systems, the safer choice is the one that preserves clear approval gates and keeps credential handling inside governed workflows.
👉 Read our full editorial: AI coding assistants expose the gap between speed and production safety