Skip to content
ATAI Today Brief
HomeNewsConceptsGuidesToolbox
AboutSubscribeUA
Subscribe

AI Today Brief

The daily AI-engineering brief. Built in public. EN · UA.

XTelegramLinkedInYouTubeRSS
NewsDigestsConceptsGuidesSubscribeAdvertiseAboutEditorial policyAI disclosurePrivacyTerms

© 2026 AI Today Brief. All rights reserved.

  1. Home/
  2. News/
  3. Tools & releases/
  4. Anthropic Open-Sources Framework for AI-Driven Vulnerability Discovery
Tools & releases

Anthropic Open-Sources Framework for AI-Driven Vulnerability Discovery

June 5, 2026· 5 min read
OKCurated by Oleksandr Kuzmenko, AI Product Engineer·Updated June 5, 2026·Sources cited on every story
AI-assisted · editor-reviewed·How we use AI
Anthropic Open-Sources Framework for AI-Driven Vulnerability Discovery

Anthropic has released an open-source framework designed to help AI agents discover security vulnerabilities in codebases. This initiative provides developers with a structured methodology and tools to leverage large language models for proactive security testing and identifying potential weaknesses before deployment.

Why it matters

Implement this framework to enhance your secure development lifecycle with AI-powered vulnerability detection and improve codebase resilience.

TL;DR

  • 01Utilize Anthropic's open-source framework for AI-powered vulnerability detection.
  • 02Leverage LLMs for static analysis and dynamic security testing.
  • 03Integrate AI security tools into your secure development lifecycle.

Key facts

Repository Name
defending-code-reference-harness
Analysis Tools Used
Docker, ASAN, gVisor
Key Commands
/quickstart, /threat-model, /vuln-scan, /triage, /patch, /customize

The Seven-Stage Vulnerability Loop

Anthropic's open-source defending-code-reference-harness provides an autonomous reference pipeline for finding and fixing C/C++ memory vulnerabilities. Under the hood, the pipeline walks through seven stages: Build (compiles code with Docker and ASAN), Recon (a lightweight agent proposes a partition of the codebase), Find (parallel agents search for crashes), Verify (a separate grader agent reproduces the crash in a fresh container), Report, and Patch.

Sandbox Isolation and CLI Skills

Because the autonomous agents execute target code, security is a major design priority. The pipeline refuses to run outside a gVisor sandbox unless overridden. Developers can initialize the security environment using scripts/setup_sandbox.sh and execute runs via bin/vp-sandboxed. The framework includes interactive Claude Code skills such as /quickstart, /threat-model, /vuln-scan, /triage, /patch, and /customize.

Customization and Model Settings

Developers can customize the pipeline to support different languages, detectors, or vulnerability classes beyond C/C++ memory vulnerabilities by using the /customize command. Additionally, the system allows pinning subagents to specific Claude model IDs to manage performance and troubleshoot rate limits during runs.

Try it in 2 minutes

./scripts/setup_sandbox.sh
bin/vp-sandboxed run drlibs --model claude-3-5-sonnet

bash

✓ When to use

  • Testing C/C++ codebases for memory safety issues.
  • Setting up automated vulnerability scanning pipelines with Claude.

✕ When NOT to use

  • Running on untrusted code without enabling gVisor sandbox isolation.
  • Fully productionized, out-of-the-box scanning for non-C/C++ projects without prior customization.
#Claude

Sources

  • Anthropic Defending Code Reference Harness
ShareShare on XShare on LinkedIn
← Previous storyAnthropic Reports Progress Towards Recursive AI Self-ImprovementNext story →Meta Launches AI Agent for Sales and Support on Instagram and Messenger

Related stories

  • Tools & releasesClaude Fable 5 Retained Permanently on Premium Plans Following Compute and Competitor Shifts
  • Tools & releasesNotebookLM Rebranded to Gemini Notebook with Built-In Secure Cloud Computing and Code Execution
  • Tools & releasesGoogle Connects Instacart, Canva, and YouTube Music to Search AI Mode
  • Tools & releasesCapital One Open-Sources VulnHunter Agentic Code Security Tool for Claude Code

Email digest

Get the morning AI brief

One email a day — the stories that matter for engineers, founders and tech leads. Human-edited, with links to primary sources.

  • ✓120+ sources scanned daily
  • ✓Edited by a human
  • ✓1 email per day
  • ✓EN + UA

By subscribing you agree to the privacy policy.