Skip to main content
Mallory
← Back to News
ai-platform-securitybuild-pipeline-compromiseinternet-facing-service-vulnerabilitygovernment-diplomatic-threat

UK Government AI Hackathons Uncover 407 Vulnerabilities in Public Code Repositories

Emerging Technology Risk · 2 sources · Updated 3mo ago · First seen Jun 12, 2026

UK Government AI Hackathons Uncover 407 Vulnerabilities in Public Code Repositories

The UK Government Cyber Coordination Centre, working with the UK AI Security Institute and the National Cyber Security Centre, used frontier AI models in a month-long series of in-person hackathons to test public government code repositories across nine organisations. The exercise uncovered 407 findings, including authentication bypass, data exposure, and remote code execution flaws; some were previously unknown zero-days, while others had already been identified and were protected by compensating controls. Officials said all critical and high-risk exploitable weaknesses were remediated and found no evidence that the vulnerabilities had been abused.

The pilot evaluated several workflows, including multi-stage agentic pipelines, deterministic scanners enhanced with AI triage, and reusable domain-specific Claude Skills, with humans kept in the loop for validation and escalation. One notable critical issue involved legacy GitHub Actions workflows that allowed an external user to trigger arbitrary code execution on a runner through a crafted comment on an open pull request. The government said the project used about £13,000 in model tokens and concluded that structured architecture, triage, and human oversight mattered more than the specific model, with a second phase planned to expand testing to more departments, more models, and closed-source environments.

New surface, new adversariesTrack how attackers are adapting to this technology.
Track this risk
Event timeline

How this story unfolded

Events from the most recent confirmed update back to the earliest known activity.

6 events · Jun 12, 2026
  1. Reported Jun 12, 20265mo ago

    Government announces second phase of the pilot

    Following the pilot, the Government Cyber Coordination Centre said it plans a second phase that will expand to more departments, include additional models, and extend testing from public repositories into closed-source environments. It also identified integrating prioritization, review, and patch generation as the next major task.

    When AI Leaves the Lab: Testing Frontier Models in Government Cyber Defence - Case study - GOV.UK
  2. Jun 12, 20265mo ago

    Government publishes case study on AI cyber defence pilot

    The UK government published a case study describing the pilot's methods, findings, and lessons learned, including that tightly scoped AI components in structured pipelines produced the strongest results. The publication also disclosed that the month-long effort cost £13,000 in model tokens.

    When AI Leaves the Lab: Testing Frontier Models in Government Cyber Defence - Case study - GOV.UK
  3. Reported Jun 12, 20265mo ago

    Government remediates critical exploitable weaknesses

    The UK government said all critical weaknesses identified in the pilot, including all critical and high-risk exploitable issues, were remediated. It also reported no evidence that any of the identified findings had been exploited.

    When AI Leaves the Lab: Testing Frontier Models in Government Cyber Defence - Case study - GOV.UK
  4. Reported Jun 12, 20265mo ago

    Critical GitHub Actions workflow flaw is uncovered

    One notable critical vulnerability affected legacy GitHub Actions workflows in a repository supporting a key government digital service. An external user could trigger arbitrary code execution on a runner by posting a specially crafted comment on an open pull request, potentially exposing secrets and enabling wider repository compromise.

    When AI Leaves the Lab: Testing Frontier Models in Government Cyber Defence - Case study - GOV.UK
  5. Reported Jun 12, 20265mo ago

    Pilot identifies 407 findings including critical flaws

    During the exercise, participants identified 407 findings, including critical weaknesses that could lead to authentication bypass, data exposure, and remote code execution. Some findings were previously unknown, while others were already understood and mitigated by compensating controls.

    When AI Leaves the Lab: Testing Frontier Models in Government Cyber Defence - Case study - GOV.UK
  6. Reported Jun 12, 20265mo ago

    UK government runs month-long AI vulnerability hackathon pilot

    The Government Cyber Coordination Centre, working with the UK AI Security Institute and NCSC, ran a month-long series of in-person hackathons using frontier AI models to test vulnerability discovery across public government code repositories in nine organisations. Teams used structured pipelines, scanner-plus-model workflows, and domain-specific Claude Skills with human validation throughout.

    When AI Leaves the Lab: Testing Frontier Models in Government Cyber Defence - Case study - GOV.UK
Do you run this?Follow how adversaries are adapting to this technology, and where it touches your stack today.
Track This Risk
Mallory platform

See the full picture, correlated to your attack surface.

This page covers what’s public. Mallory adds the parts that aren’t: which of your assets are affected, which threat actors are using it right now, and what to deploy next.

Exposure mappingMap indicators from this story to your assets and identify affected systems in minutes.
Threat actor evidenceEvery observed campaign, victim, and pivot linked to actors named in this story.
Associated malwareMalware, exploits, and IOCs connected to the activity described here.
Detection signaturesYARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Scheduled alertsGet matching new stories delivered to your team as they break, not the next morning.
AI threadsAsk questions about this story and take action on the answers.