Vulnerability backlogs are growing faster than teams can clear them. AI writes more code and finds more flaws, while fixes still move at human speed. NIST’s National Vulnerability Database has already published twice as many CVEs in 2026 as in all of 2025, and ceased enriching most CVEs this past April.
Compounding the problem, a finding that looks safe to defer may not stay that way. Attackers now use AI to find and exploit flaws in hours, even those long written off as theoretical. In October, frontier models uncovered PHP2Shell, a pair of unauthenticated remote code execution bugs in PHP that had been dismissed as unexploitable in 2012.
Discovery and exploitation now run at machine speed. To keep up, defenders need agentic security tools that detect and remediate vulnerabilities with minimal manual effort while leaving teams in full control.
GitLab 19.6 helps teams shrink their security findings backlog. Security managers can now turn on agentic triage and remediation across entire groups of projects without scripting against the API. A new agentic flow adds exploitability context to static application security testing (SAST) findings, so teams can prioritize the ones that pose real risk. Security leaders can then track the results on a new mean time to remediation (MTTR) chart.
Find and fix faster with agentic security
GitLab 19.6 builds on a platform that finds and fixes vulnerabilities with agentic security. GitLab Duo security agents use frontier AI reasoning to examine your codebase and every merge request for the logic flaws scanners miss, while built-in scanners catch known vulnerabilities from source to runtime. Agents filter out false positives before they reach a developer's queue, then help teams prioritize the rest by severity, exploitability, reachability, and blast radius. GitLab Orbit, our native knowledge graph, grounds that reasoning in the live state of your system.
For confirmed findings, an agent writes a fix, opens a merge request, and triggers the pipeline to rerun tests and scans. If anything fails, the agent reads the logs, revises the fix, and retests. Developers review a ready-to-merge fix with the agent's rationale and confidence score. That fix goes through the same approvals as any other change, and neither developers nor agents can bypass them. Remediation keeps pace with discovery, and the backlog shrinks.
GitLab 19.6 advances agentic remediation
GitLab 19.6 puts agents to work across more of that backlog. It extends agentic triage and remediation to more projects, adds exploitability context to SAST findings, and charts MTTR.
Turn on agents across many projects
Agents shrink the backlog only where they run, and turning them on one project at a time doesn't scale to thousands. Automated triage and remediation (ATR) profiles let security managers turn on agentic flows across many projects at once. In the first week after ATR profiles became accessible via API, one customer applied them to 136 projects, saving significant time.
A single profile turns on flows like false-positive detection, risk contextualization, and vulnerability resolution. Security managers choose one of three presets — Conservative, Standard, or Proactive — to set which severity levels each flow addresses and whether it runs automatically or only on demand.
Until now, applying an ATR profile required writing a script. In 19.6, security managers select projects by group or attribute from the Security Inventory or the security configuration page, choose a profile, and apply it. Afterward, Security Inventory shows which projects have a flow turned on, alongside their scanner coverage.
ATR profiles are available to GitLab Ultimate customers on all GitLab offerings. To use them, follow the ATR profile setup steps.
Assess the exploitability of SAST findings with Vulnerability Context Flow
Without exposure context, a SAST finding in an isolated internal service looks as urgent as the same finding in a public-facing service that handles sensitive data.
Vulnerability Context Flow identifies and analyzes the affected service, even in a monorepo, and adds a risk table to the SAST finding. The table shows whether exploiting the flaw requires authentication or elevated authorization, whether the service handles sensitive data, and whether it is exposed to untrusted input. Teams can then rank the backlog by exploitability as well as severity.
Vulnerability Context Flow is in beta for GitLab Ultimate customers on all GitLab offerings in 19.6. To turn it on, follow the Vulnerability Context Flow setup.
See mean time to remediation at a glance
Security leaders track MTTR to understand how long vulnerabilities stay open and whether that window is shrinking. The security dashboard now charts weekly MTTR for findings in first-party code and third-party dependencies, at the project, group, and organization level. The chart shows MTTR alongside the number of vulnerabilities fixed each week. You can group results by severity or scan type and filter by project.
The chart includes vulnerabilities that have been resolved or are no longer detected, and excludes dismissed ones. To keep longstanding findings from distorting the trend, each week counts only vulnerabilities detected in the 90 days before that week began.
The MTTR chart is on by default for GitLab Ultimate customers in 19.6. To check the prerequisites, see the security dashboard documentation.
Turn on Business Logic Security Analyzer, with Claude Mythos 5.2 on request
GitLab Ultimate customers on GitLab.com can now turn on Business Logic Security Analyzer (BLSA) themselves. BLSA scans your repository the way a security engineer would, uncovering broken ownership logic, missing authorization checks, and multi-step abuse paths.
BLSA is in beta for GitLab Ultimate customers in 19.6. On GitLab.com, turn it on by following the business logic scanning setup. On GitLab Self-Managed and GitLab Dedicated, contact us for access. To power BLSA with Anthropic's Claude Mythos 5.2, contact your account team.
Get started with agentic remediation in GitLab 19.6
Apply an automated triage and remediation profile to a project with a large backlog, and turn on Vulnerability Context Flow to rank the remaining SAST findings by exploitability. In the coming weeks, track the results on the MTTR chart. To catch the flaws scanners miss, turn on Business Logic Security Analyzer, now available via self-service on GitLab.com.
These features require GitLab Ultimate. Try GitLab Ultimate for free to test agentic security on your own projects.





