Mark RadarMARK RADAR
About
EN
Sign in

Anthropic Launches Claude Code Security to Help Development Teams Automatically Patch Code Vulnerabilities

3 reports · First detected 2026-02-23 · Last active 2026-02-23

Traditional static analysis relies heavily on established rules and can miss flaws involving data flows across components, business logic and access controls. Security teams also struggle to process large vulnerability backlogs. Anthropic has therefore integrated Claude’s code-reasoning capabilities into defensive workflows, enabling AI to scan and validate code and propose patches, though developers must still approve any fixes.

Anthropic launched the Claude Code Security research preview on February 20, 2026. Powered by Claude Opus 4.6, it scans and validates code and proposes patches, and has identified more than 500 vulnerabilities in open-source projects. The company released a six-stage reference workflow on May 27. As of May 22, it had disclosed 1,596 vulnerabilities, 97 of which had been fixed.

All Coverage

3 original reports

The Backstory

The history behind this event
Anthropic Adds Claude Mythos 5 to Enterprise Security Scanning2026-08-24 · 2 reports · similarity 0.82

Software supply chains have become a critical attack surface as enterprises rely on sprawling codebases and third-party components. Anthropic is integrating its advanced Claude Mythos 5 model into Claude Security, positioning the service as an automated way to trace data flows, identify vulnerabilities and recommend fixes. The offering is aimed at helping enterprise security teams review repositories faster while reducing the manual effort required for complex, cross-file code analysis.

As of Aug. 24, 2026, the Mythos 5-powered capability is available in public testing for Claude Enterprise customers and can connect directly to GitHub repositories. Anthropic is limiting access to reduce the risk that the model could be used to generate exploit scripts: users receive vulnerability reports and remediation recommendations but cannot interact with Mythos 5 through direct prompts. The restricted interface gives companies access to frontier scanning capabilities without exposing the underlying model as a general-purpose security tool.

Flaws Expose Claude Code, Gemini CLI and Codex to GitHub Issue Attacks2026-08-10 · 1 reports · similarity 0.83

Anthropic’s Claude Code, Google’s Gemini CLI and OpenAI’s Codex are increasingly embedded in code review and CI/CD workflows, where they can read and modify repositories, execute shell commands and access credentials. That privileged role makes them a new software-supply-chain attack surface. If an agent treats attacker-controlled GitHub issues as trusted context, a prompt injection can cross tool-permission and sandbox boundaries, turning an ordinary public contribution into code execution or secret theft.

At Black Hat USA on Aug. 5, 2026, Novee Security researcher Elad Meged showed that an unprivileged user could plant a malicious GitHub issue that compromised later agent stages. The flaws enabled remote code execution, API-key exfiltration or persistent instruction poisoning. Google rated the Gemini CLI bug CVSS 10.0 and fixed it in version 0.39.1, while Anthropic patched Claude Code in 2.1.163. OpenAI also hardened Codex by separating workflow stages and their writable state.

Apple Credits Claude, Codex in Sweeping Security Update2026-07-31 · 1 reports · similarity 0.82

Apple’s operating systems span phones, computers, watches and other devices, making flaws in the kernel and WebKit a broad security concern. Successful exploitation can lead to memory corruption, data exposure or application crashes. The latest acknowledgements are also notable because they name AI-assisted research involving Anthropic’s Claude and OpenAI’s Codex Security, showing that generative AI is moving beyond software development into vulnerability discovery and putting pressure on vendors to shorten patch cycles.

On July 27, 2026, Apple released iOS 26.6, iPadOS 26.6, macOS Tahoe 26.6, Safari 26.6 and updates for older macOS versions, tvOS, visionOS and watchOS. The release cycle listed 30 distinct kernel CVEs across Apple’s operating systems. Apple credited Anthropic researchers and Claude for work tied to WebKit, WebKit Storage and WebDAV, while Codex Security appeared in acknowledgements for WebKit Canvas alongside Calif.io, Z.AI’s GLM, NVIDIA’s AI Red Team and other security researchers.

Anthropic Launches Multi-Agent Claude Code Security Plugin2026-07-23 · 3 reports · similarity 0.89

Claude Code is Anthropic’s terminal-based AI coding tool, designed to inspect and modify repositories from a developer’s command line. Anthropic had already moved its managed Claude Security service into public beta for Enterprise customers on April 30, 2026. Bringing comparable context-aware vulnerability analysis directly into Claude Code matters because it pushes generative AI beyond code production into security review, where conventional rule-based scanners can miss flaws spanning multiple files and business logic. Human approval remains central to any proposed fix.

Anthropic said on July 22, 2026, that the Claude Security plugin beta is available to all Claude Code users. Its multi-agent system maps a repository’s architecture, builds a threat model, traces data flows and independently reviews findings. Developers can scan a full codebase or Git change sets, including branches, pull requests and individual commits, from the terminal using their existing Claude inference allowance. Findings can be exported in Markdown or JSONL, then converted into proposed patches for review and application. Anthropic cautioned that broader scans may run longer and consume substantial tokens.

Microsoft Discloses Claude Code Prompt-Injection Flaw That Could Leak CI/CD Credentials2026-06-07 · 1 reports · similarity 0.85

Anthropic’s Claude Code is a development environment that uses generative AI to help developers read and write code and operate tools. Prompt injection can override a user’s intent if the system mistakes text in a GitHub repository for trusted instructions. Microsoft said the flaw posed a significant risk because CI/CD systems often hold highly privileged credentials such as deployment keys and cloud tokens.

Microsoft security researchers recently disclosed that attackers could hide malicious prompts in GitHub content, inducing Claude Code to execute unintended commands and send CI/CD credentials to an external destination. Anthropic has patched the flaw. Users of version 2.1.128 and earlier are advised to upgrade immediately to reduce the risk of compromise to software supply chains and deployment environments.

Anthropic Patches Claude Code GitHub Actions Flaw to Reduce Token-Leak Risk2026-06-03 · 1 reports · similarity 0.82

Claude Code GitHub Actions allows AI agents to respond to instructions and modify code within software-development workflows. If trigger identities and permissions are not rigorously checked, attackers could use malicious content to induce an agent to access sensitive information such as GitHub tokens. That could compromise code repositories and automated deployment environments, making the patch important for software supply-chain security.

Anthropic patched a permission bypass in Claude Code v1.0.94 caused by insufficient checks on GitHub App triggers. It also strengthened configuration controls and safeguards to reduce the risk of token leaks. Available information did not disclose the exact dates of the vulnerability advisory or patch, the number of affected organizations, any financial losses or known cases of exploitation.

Security Flaws Exposed in Anthropic’s Claude Code AI Development Tool2026-05-22 · 3 reports · similarity 0.85

Claude Code is Anthropic’s AI development assistant, with direct access to project files, command execution and development environments. A breach of its trust boundaries could therefore put source code and identity credentials at risk. Cybersecurity company Check Point found vulnerabilities in the tool’s project configuration and sandbox mechanisms, highlighting the supply-chain risks that arise when AI coding tools process external content.

Check Point recently disclosed that attackers could plant a malicious configuration file in a project, triggering remote code execution (RCE) and the theft of API keys when a user opened it with Claude Code. Two other sandbox-escape vulnerabilities had existed for nearly six months. Anthropic has patched the flaws, but researchers criticized the company for not proactively disclosing details. Users were advised to upgrade to version 2.0.65 or later.

Anthropic's Claude Code Security Launch Rattles Cybersecurity Market2026-05-04 · 3 reports · similarity 0.91

Traditional static analysis relies heavily on existing rules, making it prone to missing contextual vulnerabilities involving business logic or access controls. Anthropic is using Claude to understand entire codebases in an effort to embed security reviews into development workflows. If companies cut spending on existing tools, the valuations of platform providers such as CrowdStrike and Palo Alto Networks, as well as financial institutions' procurement decisions, could be affected.

Anthropic launched a limited research preview of Claude Code Security for enterprise customers on February 20, 2026. Pricing was not disclosed, while open-source maintainers can apply for free access. Claude Opus 4.6 has identified more than 500 vulnerabilities. On February 23, CrowdStrike, Datadog and Zscaler fell about 11%, Fortinet and Okta dropped about 6%, and Palo Alto Networks declined 3%.

Anthropic’s Claude Code Security Tool Triggers Cybersecurity Stock Selloff2026-04-10 · 2 reports · similarity 0.92

The cybersecurity industry has long relied on rules-based static analysis and manual reviews. Static tools struggle to detect contextual vulnerabilities involving business logic and access controls, while manual reviews are constrained by the supply of skilled professionals. Anthropic’s use of large language models to find vulnerabilities and draft patches could shift defenses from post-incident detection to the development stage. It is also prompting investors to reassess the pricing power and competitive barriers of traditional cybersecurity software.

Anthropic released a research preview of Claude Code Security on February 20, 2026. The tool can scan for vulnerabilities and propose patches that require human approval. On February 23, CrowdStrike, Datadog and Zscaler fell about 11%, while Fortinet and Okta dropped about 6%. CrowdStrike had lost 18% since the product’s release, wiping about $20 billion from its market value.

Claude Code Launches Cloud Auto-Fix for CI Failures and PR Monitoring2026-03-27 · 1 reports · similarity 0.82

Anthropic’s Claude Code is an AI coding tool for software developers that was initially focused mainly on writing and modifying code. Its cloud-based Auto-fix feature extends those capabilities into continuous integration and code review. The move marks a step toward AI handling the full feedback loop, from identifying errors and proposing fixes to validating the results, while engineers focus more on review and decision-making.

As of July 20, 2026, Claude Code has formally launched cloud-based Auto-fix, which continuously monitors pull requests. When it detects a failed CI test, the feature automatically analyzes the cause, modifies the code and reruns validation. It can also revise code in response to review comments. Anthropic has not yet disclosed pricing or the full scope of support, but the core aim is for developers to return to a project and find that their PR is passing again.

Mark Radar|MARK RADAR

If you search news on Google, you can set Mark Radar as a preferred source—our coverage will show up more often in your results. Set as preferred source on Google →

All times are in Taipei time (GMT+8)