CVE-2026-32626 AnythingLLM has a Streaming Phase XSS to RCE via LLM Response Injection

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. In 1.11.1 and earlier, AnythingLLM Desktop contains a Streaming Phase XSS vulnerability in the chat rendering pipeline that escalates to Remote Code Execution on the host OS...

SUSE CVE-2026-27940

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the ggufinitfromfileimpl in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread writes 528+ bytes of attacker-controlled data past the buffer boundary. This is...

Malicious code in spectral-corsair-my-backdoor (npm)

Malicious package detected. Suspicious preinstall script exfiltrates data to a remote server. Multiple YARA rules and LLM analysis confirm. --- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 0826a28f7948e68cdddd6260a01c3653a7f04deb2c9368054243ed47713ee353 The packa...

MAL-2026-1374 Malicious code in spectral-corsair-my-backdoor (npm)

Malicious package detected. Suspicious preinstall script exfiltrates data to a remote server. Multiple YARA rules and LLM analysis confirm. --- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 0826a28f7948e68cdddd6260a01c3653a7f04deb2c9368054243ed47713ee353 The packa...

Detecting and analyzing prompt abuse in AI tools

This second post in our AI Application Security series is all about moving from planning to practice. AI Application Series 1: Security considerations when adopting AI tools established how AI adoption expands the attack surface and our threat-modelling guidance on the Microsoft security blog...

DRUPAL-CONTRIB-2026-028

The module and certain submodules AI Automators, AI Translate, AI API Explorer, AI Content Suggestions provide the ability to use an LLM to generate HTML or Markdown and preview it in a browser. Under certain circumstances, rendering of this HTML can lead to exposing secret communications in the...

AttriGuard: Defeating Indirect Prompt Injection in LLM Agents Via Causal Attribution of Tool Invocations

LLM agents are highly vulnerable to Indirect Prompt Injection IPI, where adversaries embed malicious directives in untrusted tool outputs to hijack execution. Most existing defenses treat IPI as an input-level semantic discrimination problem, which often fails to generalize to unseen payloads. We...

rami-kali-MCP

Red Team MCP Server MCP Model Context Protocol server that...

CLIOPATRA: Extracting Private Information from LLM Insights

As AI assistants become widely used, privacy-aware platforms like Anthropic's Clio have been introduced to generate insights from real-world AI use. Clio's privacy protections rely on layering multiple heuristic techniques together, including PII redaction, clustering, filtering, and LLM-based...

OpenAnt LLM-Based Vulnerability Discovery

OpenAnt from Knostic is an open source LLM-based vulnerability discovery product that helps defenders proactively find verified security flaws while minimizing both false positives and false negatives. Stage 1 detects. Stage 2 attacks. What survives is real...

Targeted Bit-Flip Attacks on LLM-Based Agents

Targeted bit-flip attacks BFAs exploit hardware faults to manipulate model parameters, posing a significant security threat. While prior work targets single-step inference models e.g., image classifiers, LLM-based agents with multi-stage pipelines and external tools present new attack surfaces,...

Evaluating Generalization Mechanisms in Autonomous Cyber Attack Agents

Autonomous offensive agents often fail to transfer beyond the networks on which they are trained. We isolate a minimal but fundamental shift -- unseen host/subnet IP reassignment in an otherwise fixed enterprise scenario -- and evaluate attacker generalization in the NetSecGame environment. Agent...

SUSE CVE-2026-25802

New API is a large language mode LLM gateway and artificial intelligence AI asset management system. Prior to version 0.10.8-alpha.9, a potential unsafe operation occurs in component MarkdownRenderer.jsx, allowing for Cross-Site ScriptingXSS when the model outputs items containing tag. Version...

CVE-2025-12345 LLM-Claw Agent Deployment initiate.c agent_deploy_init buffer overflow

A security vulnerability has been detected in LLM-Claw 0.1.0/0.1.1/0.1.1a/0.1.1a-p1. The affected element is the function agentdeployinit of the file /agents/deploy/initiate.c of the component Agent Deployment. Such manipulation leads to buffer overflow. It is possible to launch the attack...

CVE-2025-12345 LLM-Claw Agent Deployment initiate.c agent_deploy_init buffer overflow

A security vulnerability has been detected in LLM-Claw 0.1.0/0.1.1/0.1.1a/0.1.1a-p1. The affected element is the function agentdeployinit of the file /agents/deploy/initiate.c of the component Agent Deployment. Such manipulation leads to buffer overflow. It is possible to launch the attack...

Neurosymbolic Learning for Advanced Persistent Threat Detection under Extreme Class Imbalance

The growing deployment of Internet of Things IoT devices in smart cities and industrial environments increases vulnerability to stealthy, multi-stage advanced persistent threats APTs that exploit wireless communication. Detection is challenging due to severe class imbalance in network traffic,...

Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking

Jailbreak techniques for large language models LLMs evolve faster than benchmarks, making robustness estimates stale and difficult to compare across papers due to drift in datasets, harnesses, and judging protocols. We introduce JAILBREAK FOUNDRY JBF, a system that addresses this gap via a...

CVE-2026-3071

The CVE concerns Flair’s LanguageModel class where deserialization of untrusted data in versions 0.4.1 to latest allows arbitrary code execution when loading a malicious model. The issue, with CVSSv3.1 metrics indicating HIGH severity (Local access, no user interaction, full scope and high confid...

CVE-2026-3071

Deserialization of untrusted data in the LanguageModel class of Flair from versions 0.4.1 to latest are vulnerable to arbitrary code execution when loading a malicious model...

PT-2026-22151

Name of the Vulnerable Software and Affected Versions Flair versions 0.4.1 through latest Description The deserialization of untrusted data in the LanguageModel class can lead to arbitrary code execution when loading a malicious model. Recommendations Versions prior to 0.4.1 are not affected. At...