Skip to main content
Mallory
← Back to News
ai-platform-securitycloud-misconfigurationinternet-exposed-serviceleaked-secret-api-key

AI-Generated Code Accelerates Development but Expands Application Security Risk

Emerging Technology Risk · 5 sources · Updated 3mo ago · First seen Sep 3, 2026

AI-Generated Code Accelerates Development but Expands Application Security Risk

Microsoft is expanding agentic software development across GitHub Copilot, Aspire, Windows development environments, WSL, and model-context-protocol integrations, with Distinguished Engineer David Fowler saying manual line-by-line coding is becoming less central. However, automated code generation continues to produce material security defects: Veracode’s 2026 benchmark found known vulnerabilities in roughly 44% of AI code-generation tasks, while Sonar’s evaluation of GPT-5.6 variants found higher bug and vulnerability densities than GPT-5.5 despite improved functional-task pass rates, including cryptographic misconfiguration, insecure resource handling, and concurrency flaws. Microsoft is deploying its MDASH agentic scanner across engineering environments to identify vulnerabilities at scale.

Security researchers also found exploitable weaknesses in rapidly built “vibe-coded” applications, including client-side-only authentication, browser-exposed API keys, permissive or missing Supabase Row-Level Security policies, and internet-exposed internal tools. Tests of GitHub Copilot’s GPT-4o recommendations showed proposed fixes for a Node.js path-traversal flaw could be bypassed by relative or URL-encoded traversal payloads. Organizations should require human architectural and security review of AI-produced changes and retain secure-by-default libraries, SAST, software-composition analysis, secret scanning, pull-request controls, backend secret management, and deny-by-default database access policies.

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.

10 events · 2026 – Apr 2026
  1. Reported Sep 5, 20263mo ago

    David Fowler says manual code typing is becoming obsolete

    Microsoft Distinguished Engineer David Fowler said that “typing code is absolutely over,” describing a shift toward AI agents performing more implementation work while developers retain responsibility for architecture, validation, testing, dependencies, and security review.

    Microsoft engineer says "typing code is absolutely over," and Windows 11 is already being built that way
  2. Reported Sep 5, 20263mo ago

    Microsoft expands MDASH agentic vulnerability hunting across engineering systems

    Microsoft deployed its MDASH agentic vulnerability-scanning system across major engineering environments, including Windows, Azure, and identity systems. The Windows security team said it enabled deeper vulnerability hunting involving the Windows kernel, Hyper-V, and networking stack.

    Microsoft engineer says "typing code is absolutely over," and Windows 11 is already being built that way
  3. Reported Aug 6, 20264mo ago

    Sonar evaluates GPT-5.6 Sol and Terra on Java coding tasks

    Sonar evaluated GPT-5.6 Sol, GPT-5.6 Terra, and GPT-5.5 on 4,444 Java tasks using SonarQube analysis. Sol achieved the highest functional pass rate, but both GPT-5.6 variants had higher bug and vulnerability densities, particularly for concurrency defects, cryptographic misconfiguration, and insecure resource handling.

    An Evaluation of OpenAI GPT-5.6 Sol & Terra | Sonar
  4. Apr 2026

    Microsoft Aspire team cautions that code generation is not application delivery

    Microsoft's Aspire team stated that AI agents can effectively write code, but generating code is distinct from delivering a complete working application. Aspire supports agent actions including starting services, inspecting logs and telemetry, restarting failed components, and retesting applications.

    Microsoft engineer says "typing code is absolutely over," and Windows 11 is already being built that way
  5. Feb 2026

    GitHub adds Windows development environments to Copilot coding agent

    GitHub added Windows development environments to its Copilot coding agent, enabling the agent to build and test Windows-targeted projects, run linters, and verify builds.

    Microsoft engineer says "typing code is absolutely over," and Windows 11 is already being built that way
  6. 2026

    Veracode benchmark finds vulnerabilities in AI-generated code tasks

    Veracode's 2026 GenAI Code Security Report found that approximately 44% of tested AI code-generation tasks produced code containing a known vulnerability in a controlled benchmark.

    Microsoft engineer says "typing code is absolutely over," and Windows 11 is already being built that way
  7. Reported Sep 18, 20251y ago

    Lovable responds to Wiz's vibe-coding security research

    After Wiz shared its findings with Lovable's security team, Lovable published security best-practice guidance and collaborated on a global system-prompt change intended to discourage embedding secrets in client-side code.

    Wiz Research Finds Risks in 20% of Vibe-Coded Apps | Wiz Blog
  8. Reported Sep 18, 20251y ago

    Wiz identifies recurring security flaws in vibe-coded applications

    Wiz Research identified client-side-only authentication, browser-exposed credentials, permissive or absent Supabase Row-Level Security, and publicly accessible internal applications in vibe-coded apps. Reported examples included an enterprise game exposing users' PII and IP addresses.

    Wiz Research Finds Risks in 20% of Vibe-Coded Apps | Wiz Blog
  9. Reported Jun 6, 20251y ago

    Wiz releases open-source secure rules files for AI coding assistants

    Wiz released baseline open-source security rules files and the prompt used to generate them, targeting common languages and frameworks for use with AI coding assistants. The guidance promotes concise, scoped rules and conventional controls such as SAST, SCA, secret scanning, and pull-request review.

    Secure AI Vibe Coding with Rules Files | Wiz Blog
  10. Reported Mar 20, 20252y ago

    GPT-4o Copilot remediation proposals fail against path traversal example

    An evaluation of GPT-4o through GitHub Copilot found that its proposed checks for a deliberately vulnerable Node.js bank-statement API could be bypassed by relative and URL-encoded traversal payloads. The assessment concluded that LLM suggestions lack sufficient source-to-sink context to serve as standalone vulnerability remediation.

    Will You Accept These GPT 4o Secure Coding Recommendations?
Linked entities

Related entities

Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.

Open in app →

Organizations

3 linked
LovableMicrosoft CorporationGitHub
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.