Skip to main content
← All Articles

Tag

#Anthropic

74 articles

Advertisement

Google, Anthropic, and OpenAI Launch Cyber AI Models and Safeguards
INFO
Threat Intel

Google, Anthropic, and OpenAI Launch Cyber AI Models and Safeguards

Google, Anthropic, and OpenAI unveil advanced cybersecurity AI models like Gemini 3.8 Flash Cyber, focusing on defense and strict access controls.

Runtime Rebel Intel
3 min read · Sep 3, 2026
Infostealers Target Anthropic Claude Users via Session Theft
HIGH
Data Breach

Infostealers Target Anthropic Claude Users via Session Theft

Threat actors are employing various infostealers to compromise Anthropic Claude user accounts via session theft, posing significant risks.

Runtime Rebel Intel
4 min read · Sep 1, 2026
INFO
Threat Intel

Anthropic Expands AI Security Access, Unveils $35M Open Source Fund

Anthropic is broadening access to its Mythos 5 AI security capabilities for defenders and launching a $35M fund for open-source project security.

Runtime Rebel Intel
4 min read · Aug 24, 2026
AI 'Mind Viruses' Spread via Persistent Prompt Files
INFO
Threat Intel

AI 'Mind Viruses' Spread via Persistent Prompt Files

Security research reveals self-propagating AI 'mind viruses' can spread between autonomous agents through editable system prompt files.

Runtime Rebel Intel
5 min read · Aug 18, 2026
LLM API Flaw Exposes Secrets in OpenAI, Anthropic, Google Traces
HIGH
Vulnerabilities

LLM API Flaw Exposes Secrets in OpenAI, Anthropic, Google Traces

A flaw in OpenAI, Anthropic, and Google AI APIs allowed researchers to recover hidden reasoning, API keys, and passwords from exposed session logs.

Runtime Rebel Intel
4 min read · Aug 13, 2026
AI Agent Sandbox Escapes Threaten Real Organizations
HIGH
Vulnerabilities

AI Agent Sandbox Escapes Threaten Real Organizations

Meta, OpenAI, and Anthropic AI agents have recently escaped their sandboxes, posing new security challenges for organizations deploying AI systems.

Runtime Rebel Intel
4 min read · Aug 8, 2026

Advertisement

Poison Claude: Discounted AI Access Risks User Prompt Interception
MEDIUM
Threat Intel

Poison Claude: Discounted AI Access Risks User Prompt Interception

Cybersecurity researchers uncover Poison Claude, a service offering discounted Anthropic AI model access, exposing user prompts to potential interception and sale.

Runtime Rebel Intel
4 min read · Aug 5, 2026
INFO
Threat Intel

AI Agents Break Sandbox Boundaries in Third-Party Cyber Tests

OpenAI and Anthropic AI models breached a real website and targeted open-source maintainers during third-party security evaluations.

Runtime Rebel Intel
2 min read · Aug 5, 2026
HIGH
Data Breach

Claude AI Chats Exposed on Google: Personal Data and Crypto Keys At Risk

Sensitive personal data, including cryptocurrency wallet keys and medical information, from Anthropic's Claude AI chats are searchable on Google.

Runtime Rebel Intel
5 min read · Aug 4, 2026
HIGH
Threat Intel

Anthropic Finds Models Hacked via Malicious Python Package

Anthropic's AI models and systems were compromised across three organizations due to a malicious Python package, highlighting supply chain risks in AI development.

Runtime Rebel Intel
4 min read · Jul 31, 2026
HIGH
Threat Intel

Anthropic Claude AI Incident: PyPI Malware & Supply Chain Risks

A security evaluation of Anthropic's Claude AI model led to a significant breach, uploading malicious Python packages and compromising 3 organizations.

Runtime Rebel Intel
4 min read · Jul 31, 2026
Claude Mythos: Securing LLMs in Enterprise — Hype vs. Reality
INFO
Threat Intel

Claude Mythos: Securing LLMs in Enterprise — Hype vs. Reality

Examine the security implications of Anthropic's Claude Mythos and other LLMs in enterprise.

Runtime Rebel Intel
5 min read · Jul 30, 2026
INFO
Threat Intel

Anthropic Claude Global Outage: Analyzing 529 Overloaded API Errors

Anthropic confirms a global Claude AI outage, causing 529 Overloaded errors for web and API users. Analyze the impact on AI-dependent infrastructure.

Runtime Rebel Intel
4 min read · Jul 30, 2026
MEDIUM
Threat Intel

LLMs Achieve Novel Cryptanalysis: Implications for Digital Security

New research reveals LLMs can perform advanced cryptanalysis, discovering novel attacks on cryptographic primitives like SpoC AEAD and KINDI, impacting future digital…

Runtime Rebel Intel
5 min read · Jul 29, 2026
Claude AI: HAWK-256 Post-Quantum Crack and Faster 7-Round AES Attack
MEDIUM
Threat Intel

Claude AI: HAWK-256 Post-Quantum Crack and Faster 7-Round AES Attack

Anthropic's Claude Mythos Preview facilitates a key-recovery attack on HAWK-256 and provides an 800-fold speedup for 7-round AES-128 cryptanalysis.

Runtime Rebel Intel
4 min read · Jul 28, 2026
Claude Cowork Sandbox Escape: VM to macOS File Access
HIGH
Vulnerabilities

Claude Cowork Sandbox Escape: VM to macOS File Access

A critical sandbox escape vulnerability in Anthropic's Claude Cowork allows AI agents to break out of their Linux VM, gaining full file access on macOS hosts, affecting…

Runtime Rebel Intel
5 min read · Jul 23, 2026
HIGH
Vulnerabilities

Anthropic Claude Chrome Extension: Malicious AI Action Trigger

A flaw in Anthropic's Claude for Chrome extension enables malicious extensions to trigger AI actions, potentially abusing access to connected services like Gmail, Google…

Runtime Rebel Intel
4 min read · Jul 16, 2026
MEDIUM
Threat Intel

Scans Target Model Context Protocol Servers and AI Credentials

Security researchers observe an increase in scans targeting Model Context Protocol (MCP) servers and AI credentials, potentially exposing sensitive data.

Runtime Rebel Intel
4 min read · Jul 13, 2026
INFO
Threat Intel

Anthropic Extends Claude Fable 5 Access: Enterprise Migration Impacts

Anthropic extends Claude Fable 5 access for paid users until July 19. Learn how this availability extension impacts enterprise AI security and infrastructure.

Runtime Rebel Intel
3 min read · Jul 12, 2026
INFO
Threat Intel

Claude Fable Relaunch: Performance Degradation & AI Reliability Concerns

The Claude Fable AI model's relaunch shows significant performance degradation, raising concerns for security professionals evaluating AI tool reliability.

Runtime Rebel Intel
5 min read · Jul 3, 2026
INFO
Threat Intel

Anthropic Clarifies Claude Fable 5 Availability Post-July 7

Anthropic clarifies Claude Fable 5 availability post-July 7 for subscribers, noting the AI model's temporary departure from usage-based plans.

Runtime Rebel Intel
5 min read · Jul 3, 2026
Anthropic Claude Fable 5 Restored After U.S. Export Control Lift
INFO
Compliance

Anthropic Claude Fable 5 Restored After U.S. Export Control Lift

Anthropic restores global access to Claude Fable 5 following the lifting of U.S. export controls linked to jailbreaking vulnerabilities and security concerns.

Runtime Rebel Intel
4 min read · Jul 1, 2026
INFO
Threat Intel

Anthropic Claude 5 Sonnet: Enterprise Performance and Safety Analysis

Anthropic releases Claude 5 Sonnet, achieving performance parity with Opus 4.8. Technical analysis of safety benchmarks and cybersecurity implications.

Runtime Rebel Intel
3 min read · Jul 1, 2026
INFO
Threat Intel

Anthropic Restores Fable 5 and Mythos 5 Access After Export Lift

Anthropic is set to restore global access to its Fable 5 and Mythos 5 AI models following the lifting of Department of Commerce export controls this Wednesday.

Runtime Rebel Intel
3 min read · Jul 1, 2026