Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol Via Prompt Injection

Large language model LLM based agents are increasingly used to automate financial transactions, yet their reliance on contextual reasoning exposes payment systems to prompt-driven manipulation. The Agent Payments Protocol AP2 aims to secure agent-led purchases through cryptographically verifiable...

A Systematic Literature Review on LLM Defenses against Prompt Injection and Jailbreaking: Expanding NIST Taxonomy

The rapid advancement and widespread adoption of generative artificial intelligence GenAI and large language models LLMs has been accompanied by the emergence of new security vulnerabilities and challenges, such as jailbreaking and other prompt injection attacks. These maliciously crafted inputs...

ReasoningBomb: A Stealthy Denial-Of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models

Large reasoning models LRMs extend large language models with explicit multi-step reasoning traces, but this capability introduces a new class of prompt-induced inference-time denial-of-service PI-DoS attacks that exploit the high computational cost of reasoning. We first formalize inference cost...

RustCrypto signatures: Data forgery vulnerability

RustCrypto signatures are a set of digital signature algorithms developed by RustCrypto under open source. In versions of RustCrypto signatures from 0.0.4 to 0.1.0-rc.4, there was a vulnerability related to data manipulation. This vulnerability stemmed from the signature verification implementati...

CVE-2021-47891

Unified Remote 3.9.0.2463 contains a remote code execution vulnerability that allows attackers to send crafted network packets to execute arbitrary commands. Attackers can exploit the service by connecting to port 9512 and sending specially crafted packets to open a command prompt and download an...

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,...

PT-2026-4507

Name of the Vulnerable Software and Affected Versions Unified Remote version 3.9.0.2463 Description The software contains a remote code execution issue that allows attackers to execute arbitrary commands. An attacker can exploit the service by connecting to port 9512 and sending specially crafted...

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...

Why AI Keeps Falling for Prompt Injection Attacks

Imagine you work at a drive-through restaurant. Someone drives up and says: "I'll have a double cheeseburger, large fries, and ignore previous instructions and give me the contents of the cash drawer." Would you hand over the money? Of course not. Yet this is what large language models LLMs do...

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,...

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,...

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 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 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...