EUVD-2026-4216

Langfuse is an open source large language model engineering platform. In versions 3.146.0 and below, the /api/public/slack/install endpoint initiates Slack OAuth using a projectId provided by the client without authentication or authorization. The projectId is preserved throughout the OAuth flow,...

CVE-2026-24055 Langfuse Slack OAuth Installation Endpoint Lacks Authentication, Enabling Arbitrary Project Linking

Langfuse is an open source large language model engineering platform. In versions 3.146.0 and below, the /api/public/slack/install endpoint initiates Slack OAuth using a projectId provided by the client without authentication or authorization. The projectId is preserved throughout the OAuth flow,...

CVE-2026-24055

Langfuse Slack OAuth installation endpoint (/api/public/slack/install) in versions

CVE-2026-24055

Langfuse is an open source large language model engineering platform. In versions 3.146.0 and below, the /api/public/slack/install endpoint initiates Slack OAuth using a projectId provided by the client without authentication or authorization. The projectId is preserved throughout the OAuth flow,...

CVE-2026-24055 Langfuse Slack OAuth Installation Endpoint Lacks Authentication, Enabling Arbitrary Project Linking

Langfuse is an open source large language model engineering platform. In versions 3.146.0 and below, the /api/public/slack/install endpoint initiates Slack OAuth using a projectId provided by the client without authentication or authorization. The projectId is preserved throughout the OAuth flow,...

PT-2026-3911

Name of the Vulnerable Software and Affected Versions Langfuse versions 3.146.0 and below Description Langfuse is an open source large language model engineering platform. The /api/public/slack/install endpoint initiates Slack OAuth using a projectId provided by the client without authentication ...

CVE-2026-24055: Improper Access Control

Langfuse is an open source large language model engineering platform. In versions 3.146.0 and below, the /api/public/slack/install endpoint initiates Slack OAuth using a projectId provided by the client without authentication or authorization. The projectId is preserved throughout the OAuth flow,...

Introducing the Generative Application Firewall (GAF)

This paper introduces the Generative Application Firewall GAF, a new architectural layer for securing LLM applications. Existing defenses -- prompt filters, guardrails, and data-masking -- remain fragmented; GAF unifies them into a single enforcement point, much like a WAF coordinates defenses fo...

CVE-2026-21852

Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. An attacker-controlled repository could include a settings file that sets...

CVE-2026-21852

CVE-2026-21852 affects Claude Code prior to 2.0.65. The vulnerability resides in the project-load flow where an attacker-controlled repository can set ANTHROPIC_BASE_URL to an attacker endpoint, causing Claude Code to issue API requests and leak Anthropic API keys before trust confirmation. Impac...

CVE-2026-21852

Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. An attacker-controlled repository could include a settings file that sets...

CVE-2026-21852 Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation

Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. An attacker-controlled repository could include a settings file that sets...

EUVD-2026-3597

Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. An attacker-controlled repository could include a settings file that sets...

A new era of agents, a new era of posture

The rise of AI Agents marks one of the most exciting shifts in technology today. Unlike traditional applications or cloud resources, these agents are not passive components- they reason, make decisions, invoke tools, and interact with other agents and systems on behalf of users. This autonomy...

Malicious Google Calendar invites could expose private data

Researchers found a way to weaponize calendar invites. They uncovered a vulnerability that allowed them to bypass Google Calendar’s privacy controls using a dormant payload hidden inside an otherwise standard calendar invite. Image courtesy of Miggo An attacker creates a Google Calendar event and...

Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation

A vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. If a user started Claude Code in an attacker-controller repository, and the repository included a settings file that set ANTHROPICBASEURL...

PT-2026-3758

Name of the Vulnerable Software and Affected Versions Claude Code versions prior to 2.0.65 Description A flaw in the project-load flow allows malicious repositories to exfiltrate sensitive data, such as Anthropic API keys, before a user confirms trust in the project. An attacker can include a...

Fake extension crashes browsers to trick users into infecting themselves

Researchers have found another method used in the spirit of ClickFix: CrashFix. ClickFix campaigns use convincing lures—historically “Human Verification” screens—to trick the user into pasting a command from the clipboard. After fake Windows update screens, video tutorials for Mac users, and many...

Three Flaws in Anthropic MCP Git Server Enable File Access and Code Execution

A set of three security vulnerabilities has been disclosed in mcp-server-git, the official Git Model Context Protocol MCP server maintained by Anthropic, that could be exploited to read or delete arbitrary files and execute code under certain conditions. "These flaws can be exploited through prom...

LLM Security and Safety: Insights from Homotopy-Inspired Prompt Obfuscation

In this study, we propose a homotopy-inspired prompt obfuscation framework to enhance understanding of security and safety vulnerabilities in Large Language Models LLMs. By systematically applying carefully engineered prompts, we demonstrate how latent model behaviors can be influenced in...