Advertisement
AI Coding Agents Vulnerable to Friendly Fire Command Execution
AI coding agents like Anthropic's Claude Code and OpenAI's Codex are susceptible to Friendly Fire attacks, leading to unintended local code execution.
AI Coding Agents Mimic Malicious Activity in Endpoint Detections
AI coding agents like Claude Code and OpenAI Codex are triggering endpoint security alerts by performing actions similar to human attackers, demanding rule adjustments.
Claude Code Indirect Prompt Injection: Hijacking Developer Machines
Researchers demonstrate a new attack method leveraging indirect prompt injection in Claude Code, enabling the hijack of developer machines via malicious code in…
Anthropic Claude Code GitHub Action Flaw Enables Repo Hijacking
A critical flaw in Anthropic's Claude Code GitHub Action allowed attackers to hijack public repositories using malicious issues, posing supply chain risks.
Anthropic Claude Code Integration of Mythos Model Raises Security Risks
Anthropic may be integrating its restricted Mythos model into Claude Code, raising concerns about autonomous agentic capabilities and AI safety levels.
Claude Code Sandbox Bypass: Anthropic Patches CLI Vulnerability
Anthropic recently addressed a sandbox bypass in Claude Code. This vulnerability could have allowed data exfiltration when combined with prompt injection.
Advertisement
AI CLI Tools Vulnerable to RCE via Malicious Repositories
TrustFall research reveals RCE risks in Claude Code and Cursor CLI. AI agents can be manipulated via malicious repositories to execute arbitrary commands.
Claude Code and Gemini CLI: Prompt Injection via Code Comments
Research reveals how Claude Code, Gemini CLI, and GitHub Copilot agents are vulnerable to prompt injection attacks via malicious source code comments.
Anthropic Claude Code Vulnerability Analysis — Mitigation Guide
Anthropic's Claude Code faces critical scrutiny following a source code leak and the discovery of a vulnerability allowing arbitrary command execution.
Fake GitHub Repositories Deliver Vidar Infostealer via Claude Leak
Threat actors are exploiting the Claude Code leak, deploying fake GitHub repositories to distribute Vidar infostealer malware, targeting unsuspecting developers and…
Claude Code Source Leaked via npm Packaging Error
Anthropic confirms internal Claude Code source code was leaked due to an npm packaging error. Analysis of supply chain risks and mitigation strategies.
Anthropic Claude Code Source Code Leaked via NPM Registry
Anthropic accidentally exposed proprietary source code for its Claude Code CLI tool on the public npm registry. Analyze the technical impact and risks.
Securing Claude Code: Managing AI Agent Risk with Ceros Visibility
Discover how Claude Code creates new security challenges for engineering teams and how Ceros provides the visibility needed to govern autonomous AI agents.
Claude Code Weaponized in Mexican Government Cyberattack
Analysis of how threat actors leveraged Anthropic’s Claude Code to automate exploitation and exfiltrate 150GB of data from Mexico's infrastructure ministry.
Claude Code Security Analysis: Assessing AI CLI Assistant Risks
Technical analysis of Anthropic's Claude Code CLI tool, evaluating its impact on application security and potential for introducing code vulnerabilities.
Anthropic Patches Claude Code Vulnerabilities Enabling Silent Hacking
Anthropic addressed flaws in Claude Code that allowed attackers to execute arbitrary commands on developer devices via malicious repository configurations.
Claude Code Flaws Enable RCE & API Key Exfiltration
Multiple security flaws in Anthropic's Claude Code AI coding assistant allow remote code execution and API credential theft via configuration mechanisms.