From the Anthropic edition of November 10, 2026
ControlPlane: Claude Opus and Sonnet surfaced 1,000+ issues in UK public-sector open code; 118 critical vulnerabilities reported at about $50 in tokens per service
ControlPlane (AI Security team) · Security consultancy · United Kingdom
- Publisher
- ControlPlane
- Original publication
- November 6, 2026 (page metadata modified November 9, 2026)
- Source retrieved
- 2026-11-11
What happened
ControlPlane reports that its AI Security team used Claude Opus and Sonnet to review UK public-sector open-source code, surfacing more than 1,000 issues, of which 118 critical vulnerabilities passed internal QA and were reported through the government's vulnerability reporting service; 84 were rated High or Critical, and 15 were resolved at publication. All fell within the OWASP Top Ten, including one CVSS 10.0 Microsoft 365 exposure. The firm reports about $50 in AI tokens and four hours per service, and says many findings were also identifiable with cheaper local Gemma-class models.
Why it matters
State, local and university IT teams that publish code (or whose vendors do) face the same exposure: AI-assisted scanning makes long-standing OWASP flaws cheap to find, for defenders and attackers. The reported cost per service suggests continuous AI-assisted code review could supplement annual penetration tests, but the filtering from 1,000+ issues to 118 reported means staff triage is required.
Evidence and measured results
Firm-reported counts and costs from a large scan (vulnerability totals, CVSS ratings, resolution count); not peer reviewed; underlying data not public.
Limitations and uncertainty
Self-published by a firm that sells AI security services; counts not independently verified; false-positive rate of the 1,000+ issues not reported; most vulnerability details withheld pending remediation. Cross-tagged state-government: transferable to state and local agencies that publish open-source code. Why now: the findings became public news via WIRED on Nov. 10.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-11-11; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- Public-sector code repositories carry long-standing OWASP-class flaws and exposed secrets that annual IT health checks miss.
- Stakeholders
- State or campus CISO
- Application development leads
- Vulnerability disclosure coordinator
- Open-source program office
- Discovery questions
- Which repositories are public?
- How often are they scanned, including git history?
- Who triages external vulnerability reports?
- Value hypothesis
- Low-cost AI-assisted review between annual tests could surface common flaws earlier, if triage capacity exists.
- Potential engagement
- A pilot scan of five repositories with triaged findings and remediation tracking.
- Unsupported claims
- Replacement of penetration testing
- Low false-positive rates
- Guaranteed cost of $50 per service in every environment
Pre-sales engineering
Role takeaway
- Fit
- Good fit for agencies with public or internal repositories and CI/CD.
- Architecture and integration
- Per-repo AI review job in CI/CD; findings to ticketing; secret scanning of history.
- Prerequisites
- Repository access
- Data agreement for sending code to model
- Triage staff
- Constraints
- Firm-reported results
- High volume of unfiltered findings
- Security
- Rotate exposed credentials at identity provider; restrict code sent externally where policy requires.
- Proof of value
- Measure true-positive rate on pilot repos
- Compare Claude with a local model
- Track time from finding to fix
Delivery
Role takeaway
- Work
- Stand up recurring AI-assisted code review with triage.
- Dependencies
- Code owners
- Disclosure process
- Security tooling
- Ownership
- Agency security team.
- Skills and adoption
- Developers trained on remediating OWASP Top Ten classes.
- Governance checkpoints
- Data handling approval for code
- Disclosure policy in place
- Monthly finding review
- Acceptance criteria
- Proposed: all critical findings triaged within 5 business days
- Proposed: exposed secrets rotated within 24 hours of discovery
- Risks
- Triage overload
- False positives
- Code exposure to external model
Implementation considerations
Lighthouse Advisory interpretation across the operating dimensions a public-sector buyer must settle before this evidence becomes a design. Each note answers the question under its heading for this specific source.
Architecture and integration
What must connect, and where does the AI sit in the workflow?
An AI code-review job per repository fits CI/CD pipelines, as the firm suggests; triage and disclosure workflows must scale with the volume of AI-generated findings.
Governance
Who approves, reviews and stays accountable for outcomes?
Agencies publishing code should have a vulnerability disclosure program ready for AI-driven reports.
Security and privacy
What data, permissions and controls need testing?
Findings include exposed credentials and missing access checks; secret rotation, not just deletion from repositories, is the key control.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Not addressed in the source.
Procurement
What should contracts, pricing and exit terms secure?
Compare the reported ~$50 per service token cost with annual IT health-check costs, while budgeting staff triage time; ControlPlane has a commercial interest.
Operating model
Which teams own the service once it runs?
Security teams need capacity to triage a high volume of AI-generated findings and route them to code owners.
Publication history
- 2026-11-10Anthropic · Issue 1210 resources
Stable resource ID: controlplane-claude-uk-public-sector-code-audit-118-critical-vulns-20261110