All news with #anthropic tag

🔒 Researchers disclosed an attack chain against Anthropic’s command-line coding assistant, Claude Code, that abuses the Model Context Protocol (MCP). A malicious npm post-install hook can rewrite the local ~/.claude.json configuration to redirect authenticated MCP traffic to attacker infrastructure, allowing interception of stored OAuth bearer tokens. Anthropic has been notified but has not issued a patch; defenders are advised to monitor the configuration file, treat npm post-install hooks as high risk, and rotate OAuth tokens tied to Claude Code integrations.

🔒 A researcher discovered a vulnerability in Anthropic's Claude Code GitHub Action that allowed takeover of public repositories via a single opened GitHub issue. Anthropic patched the core bypass in January and released fixes in claude-code-action v1.0.94, rating the issue 7.8 under CVSS v4.0 and issuing a bounty. The flaw arose from overly permissive triggers that trusted actors ending in "[bot]" and example workflows allowing non-write users, enabling indirect prompt injection to exfiltrate environment secrets and OIDC credentials. Administrators should update to v1.0.94, audit workflows for untrusted inputs, and remove unnecessary permissions and tools to prevent exfiltration.

🔍 At Infosecurity Europe 2026, Bugcrowd unveiled ExploitBench, a graded benchmark assessing AI models' ability to chain vulnerability discovery into staged exploits against a vulnerable V8 build. Anthropic’s Claude Mythos outperformed OpenAI’s GPT‑5.5 in head‑to‑head runs, achieving higher average scores and more top‑tier exploits, often with occasional human nudges. The report highlights rising offensive potential of frontier LLMs and urges defenders to adopt automated remediation and prioritization.

🛠️ The Amazon Bedrock console has been redesigned to match real-world model development workflows: experiment, iterate, and scale. The refreshed UI centers on the bedrock-mantle endpoint and is compatible with the OpenAI Responses API, OpenAI Chat Completions API, and the Anthropic Messages API. Users can browse and compare models, create projects to run evaluations, and get project-aware code snippets prefilled with model ID, region, endpoint URL, and API key references. The new experience is available in all Regions where the bedrock-mantle endpoint is offered.

🛡️ Security experts at Infosecurity Europe warned that expanding access to frontier AI tools for vulnerability discovery — notably Anthropic’s Project Glasswing and OpenAI’s reported GPT-5.5 Cyber pilot — heralds a structural shift in cybersecurity. Speakers advised organisations to harden controls, run incident response exercises, and accelerate adoption to avoid falling behind attackers. The panel stressed that AI augments, not replaces, human expertise; combined use improves validation and remediation of AI-discovered issues.

🛡️ Anthropic has broadened Project Glasswing, giving 150 additional organizations access to its most capable model, Claude Mythos Preview, to help find vulnerabilities in critical software. The program, first opened to roughly 50 partners in April, claims more than 10,000 high- or critical-severity flaws discovered to date. New participants span 15+ countries and underrepresented sectors like power, water, healthcare and hardware, chosen for the potential catastrophic impact of breaches. Anthropic warned that while discovery is accelerating, safe public release of Mythos-class models remains restricted due to incomplete safeguards.

🔎 Anthropic has added 150 additional companies to its Project Glasswing initiative, prioritizing critical infrastructure sectors like power, water, healthcare, communications, and hardware. Analysts view the expansion positively for increasing vulnerability discovery, but warn of a remediation bottleneck: vendors and SOCs may struggle to validate, prioritize, and patch a potential 10x or greater increase in findings. Experts emphasize the need for confidence scoring, automation, and third-party validation to maintain trust and ensure timely remediation.

🛡️ A threat actor used an AI-assisted ransomware toolkit to automate Active Directory discovery and iterate EDR evasion techniques. Researchers found Cursor and Claude Opus agents used for coding, analysis, testing, and checking public research for bypass methods, with some malware tested against Sophos, CrowdStrike, and Microsoft EDR products. Sophos determined the workflow was human-directed, while AI accelerated development, producing numerous payload modules and mapping techniques to MITRE ATT&CK.

🚀 Claude Opus 4.8 is now accessible in Microsoft Foundry, providing developers and enterprises with Anthropic’s most capable Opus model for coding, agentic tasks, and professional work. The update focuses on long-running workflows, deeper reasoning across documents and codebases, and more reliable tool use for multi-step automation. Teams can now evaluate and deploy the model within Foundry’s unified platform for building and operating AI applications.

🤖 Anthropic confirmed plans to release its Mythos-class AI models to the general public after previously restricting access because of security risks to public and private software. Initially available only to select organizations and researchers, Mythos was held back while Anthropic developed stronger safeguards. The company says it’s making swift progress and expects to offer Mythos-class models to customers in the coming weeks, noting significant gains in code reasoning and autonomy over its Opus 4.8 flagship.

🤖 AWS now offers Claude Opus 4.8, Anthropic's most capable generally available model, bringing advances in agentic coding, professional knowledge work, and autonomous long-running tasks for developers and enterprises. The model sustains longer sessions, reasons more deeply, and maintains consistency for production workflows. Customers can access Opus 4.8 via Amazon Bedrock or the Claude Platform on AWS, with AWS-managed features and unified billing.

🔍 Cisco researchers found that popular frontier LLMs from OpenAI, Anthropic, Google, xAI, and Amazon exhibit substantially higher risk when subjected to multi-turn adversarial attacks than when assessed with single-prompt safety benchmarks. The team ran tens of thousands of single-turn and multi-turn attacks across 15 models and multiple configurations, revealing wide gaps in attack success rates (ASRs) and configuration-dependent safety behavior. They urge improved benchmarks, transparency on configuration impacts, and publication of paired single- and multi-turn ASRs to better inform procurement and governance decisions.

🛡️ Researchers uncovered a malicious npm package named mouse5212-super-formatter that exfiltrates files from the /mnt/user-data directory used by Anthropic's Claude AI. OX Security describes the campaign, codenamed Malware-Slop, as a postinstall script that authenticates to GitHub using environment or hard-coded tokens, creates or targets a repository, and uploads local files to an attacker-controlled account. The package has been downloaded hundreds of times, and the linked GitHub account—created shortly before the package appeared—has since disappeared. Analysts noted the actor leaked a private token, suggesting poor OPSEC and possibly AI-assisted malware creation.

🛡️ Recent developments show AI moving from automation to autonomous cyber operations, shifting how offense and defense interact. The Anthropic Mythos Preview and related incidents illustrate models discovering and chaining vulnerabilities with limited human direction, prompting coordinated defensive responses from major vendors. Policy and procurement are adapting, and security leaders must treat AI agents as principals, invest in adaptive defenses, and reframe risk models for continuous compromise.

🔍 Anthropic and over 50 partners report Project Glasswing, using Claude Mythos Preview, has surfaced roughly 10,000 critical or high-severity vulnerabilities across open source projects and partner software. The initiative scanned more than 1,000 open-source projects and validated thousands of findings with independent security firms, but maintainers are overwhelmed by the volume and pace of disclosures. Anthropic is disclosing issues under a coordinated policy and has launched enterprise offerings like Claude Security and a Cyber Verification Program to support legitimate security research.

🛡️ Anthropic appears to be preparing a public rollout of its restricted Mythos model, which the company warned poses major security risks by automating high-quality cyberattacks. Announced in April as an advanced frontier model, Mythos showed dramatic improvements in code reasoning and autonomy compared to Opus 4.7. References briefly appeared in Claude Code and Claude Security, suggesting a controlled preview, while Anthropic builds guardrails and works with partners through its Glasswing initiative.

🔎 Anthropic disclosed that Project Glasswing and access to Claude Mythos Preview helped partners uncover over 10,000 high- or critical-severity vulnerability candidates across widely used, systemically important software since last month. Analysis verified 1,726 true positives, including 1,094 high- or critical-severity flaws, and resulted in 97 upstream patches and 88 advisories. One notable finding was a critical WolfSSL flaw (CVE-2026-5194).

🔒 Cloudflare has extended its Cloud Access Security Broker (CASB) to support the Claude Compliance API, enabling security and compliance teams to monitor Claude Enterprise activity directly in the Cloudflare dashboard without endpoint agents. The integration surfaces security findings for projects, attachments, chat files, messages, and provider-generated artifacts, and groups findings by category and severity. Customers can immediately convert findings into enforcement actions via Gateway policies and use existing detection and remediation workflows. Setup requires a Claude Enterprise account and Compliance API access, and the integration begins scanning and surfacing findings within minutes.

🔒 A security report details how a group used Anthropic’s Mythos AI model to discover a kernel memory corruption vulnerability and develop an exploit targeting Apple’s M5 platform. The article summarizes the incident and notes it was posted on May 21, 2026. It highlights implications for macOS security and the role of advanced AI tools in vulnerability discovery. The piece is concise and focused on the exploit’s origin and significance.

🛈 Amazon Bedrock now supports request-level usage attribution on the InvokeModel and InvokeModelWithResponseStream APIs, enabling customers to tag individual model inference calls with attributes such as team, project, and environment. This capability extends existing attribution options like application inference profiles, IAM principal attribution, project-level tracking on bedrock-mantle, and workspace tracking for Anthropic Claude models. Customers can enable model invocation logging in their AWS Region and include metadata in requests to analyze usage in Bedrock model invocation logs. The feature is available in all AWS commercial Regions where Amazon Bedrock is offered.