Notifications
Clear all
Topic starter
01/08/2026 8:56 pm
TL;DR: 65 to 75% of frontier AI agents’ working patches resurrect vulnerabilities already found and fixed, while functional success rose to 83 to 95% and secure-and-functional success stayed at 24 to 36%, according to Checkmarx research. The result is a widening gap between code that works and code that remains safe, making security review mandatory rather than optional.
NHIMG editorial — based on content published by Checkmarx: New research on how frontier AI agents resurrect fixed vulnerabilities
By the numbers:
- 65-75% of frontier AI agents’ working patches resurrect vulnerabilities that were already found, fixed, and buried.
- Functional success surged to 83-95% across the cohort, up from 44-61% a single model generation ago.
- Checkmarx’s 2026 Future of AppSec report found that 70% of developers say AI code generation created more vulnerabilities in their code in 2025.
Questions worth separating out
Q: What breaks when AI coding agents are allowed to ship code without security constraints?
A: Teams get working software that can still carry old, well-known vulnerabilities back into production.
Q: Why do AI coding agents keep reproducing vulnerabilities that humans already fixed?
A: Because these systems optimise for task completion and code similarity, not for preserving the security intent embedded in a patch.
Q: How can security teams tell whether AI-generated code is actually safe?
A: They should look for security regression evidence, not just test pass rates.
Practitioner guidance
- Block known-vulnerable patterns at generation time Create policy checks that reject agent output matching high-risk patterns such as traversal, unsafe deserialisation, and weak auth handling before code reaches review.
- Add security intent to the task spec Require developers to provide secure implementation constraints, forbidden APIs, and expected control behaviour before an AI agent begins generating code.
- Gate merges on security-relevant tests Make passing functional tests insufficient for merge approval by adding security regression tests tied to the vulnerability classes most likely to recur.
What's in the full report
Checkmarx's full research covers the operational detail this post intentionally leaves for the source:
- Per-CWE breakdown showing which vulnerability classes were most often resurrected by frontier AI agents.
- Intervention cost analysis comparing prompt reminders, reasoning effort, threat modelling, and post-hoc review.
- Full failure-mode taxonomy explaining how agents preserved functionality while reintroducing insecure logic.
- Benchmark design details for SusViBes and the model cohort used in the study.
👉 Read Checkmarx’s research on frontier AI agents resurrecting fixed vulnerabilities →
AI coding agents and resurrected CVEs: what practitioners need to know?
Explore further
01/08/2026 9:04 pm
AI coding quality is outpacing secure coding quality. The central finding here is not that AI agents fail to code. It is that they increasingly succeed at generating working code while failing to preserve the security properties already established in upstream fixes. That widens the governance problem for application security teams. Practitioners should stop treating secure code generation as a model-quality issue and start treating it as a pipeline assurance issue.
A question worth separating out:
Q: How should teams govern AI-generated authentication code?
A: Treat AI-generated authentication code as identity-sensitive change, not ordinary development output. Put it behind code-owner review, require negative-case tests, and verify token scope, field exposure, and database migration handling before merge. If the assistant touched passwords, sessions, or tokens, IAM and security approval should be mandatory.
👉 Read our full editorial: AI coding agents are resurrecting old CVEs in production code
