Notifications
Clear all
Topic starter
26/08/2026 11:51 am
TL;DR: AI can accelerate secure development lifecycle review, but it still overstated severity in 46% of cases and missed a known WebAuthn flaw, according to Yubico’s experience using Claude Code and Codex Security across 29 repositories. The finding is not that AI is unreliable, but that it needs tight task boundaries, human triage, and governance around refusal handling and validation depth.
NHIMG editorial — based on content published by Yubico: AI-assisted security review and secure development lifecycle observations
By the numbers:
- Yubico said its assessment covered 29 repositories across its open source software portfolio.
- Human triage downgraded approximately 46% of the AI-generated cases, most commonly from High to Medium.
- The assessment ultimately produced 448 verified findings with only a handful of false positives.
Questions worth separating out
Q: How should security teams use AI-assisted code review safely?
A: Use it as a triage layer that accelerates first-pass detection, then require a separate validation step for findings that affect access control, authentication, secrets, or release gating.
Q: Why do AI-assisted security reviews still need human triage?
A: Because the model can misread context, inflate severity, or miss compound weaknesses that only become meaningful when combined.
Q: What breaks when AI tools refuse to analyse attack chains?
A: The review process loses visibility into how small weaknesses combine into a higher-impact exploit.
Practitioner guidance
- Define bounded AI review tasks Break security analysis into narrow stages such as threat modelling, weakness enumeration, and evidence validation so the model is not asked to solve everything at once.
- Calibrate severity before remediation intake Require a human reviewer to validate every High or Critical finding before it enters the vulnerability backlog, especially where the model inferred exploitability from partial context.
- Document refusal-sensitive scenarios Track the review cases where the model refuses multi-step attack-chain analysis or combination testing so those scenarios can be routed to specialised tooling or manual review.
What's in the full article
Yubico's full post covers the operational detail this post intentionally leaves for the source:
- How the 1,000-line prompt was structured to constrain threat modelling, weakness enumeration, and evidence capture
- The repository review workflow across 29 codebases, including how two security engineers independently compared outputs
- The specific triage process used to downgrade overcalled findings and consolidate AI-assisted observations
- The control test involving the known WebAuthn issue later published as YSA-2026-02 and what the model missed
👉 Read Yubico's analysis of AI-assisted security review in the secure development lifecycle →
AI-assisted code review for security teams: what changed here?
Explore further
26/08/2026 11:51 am
AI-assisted security review is becoming a governance problem, not just a productivity upgrade. The central issue is not whether models can help find defects, but whether organisations can define the boundaries of trust around what the model is allowed to infer, refuse, and prioritise. In practice, the control failure is often not model performance alone, but the absence of a clear validation model for AI-generated security evidence. Practitioner conclusion: if the output changes risk decisions, it needs governance as well as automation.
A question worth separating out:
Q: How should organisations govern AI-assisted development in secure pipelines?
A: They should treat AI-assisted coding as a controlled workflow with explicit owners, enforced policy checks, and measurable outcomes. Put controls in the IDE, pull request, and CI/CD stages, then monitor whether remediation time, flaw density, and exception rates improve. Governance should focus on who approved the change and what policy prevented unsafe code from merging.
👉 Read our full editorial: AI-assisted code security review raises both signal and governance questions
