Reverse CAPTCHA: Evaluating LLM Susceptibility to Invisible Unicode Instruction Injection

We introduce Reverse CAPTCHA, an evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in otherwise normal-looking text. Unlike traditional CAPTCHAs that distinguish humans from machines, our benchmark exploits a capability gap: model...

CVE-2026-27933 Manyfold vulnerable to session hijack via cookie leakage in proxy caches

Manyfold is an open source, self-hosted web application for managing a collection of 3d models, particularly focused on 3d printing. Versions prior to 0.133.0 are vulnerable to session hijack via cookie leakage in proxy caches. Version 0.133.0 fixes the issue...

EUVD-2026-8776

Manyfold is an open source, self-hosted web application for managing a collection of 3d models, particularly focused on 3d printing. Versions prior to 0.133.0 are vulnerable to session hijack via cookie leakage in proxy caches. Version 0.133.0 fixes the issue...

EUVD-2026-8698

Due to an improperly configured firewall rule, the router will accept any connection on the WAN port with the source port 5222, exposing all services which are normally only accessible through the local network. This issue affects MR9600: 1.0.4.205530; MX4200: 1.0.13.210200...

PT-2026-22040

Name of the Vulnerable Software and Affected Versions Manyfold versions prior to 0.133.0 Description Manyfold is a self-hosted web application used for managing 3D models, with a focus on 3D printing. Prior to version 0.133.0, a logged-in user could achieve Remote Code Execution RCE when model...

APFuzz: Towards Automatic Greybox Protocol Fuzzing

Greybox protocol fuzzing is a random testing approach for stateful protocol implementations, where the input is protocol messages generated from mutations of seeds, and the search in the input space is driven by the feedback on coverage of both code and state. State model and message model are th...

GrandStream GXP1600 Unauthenticated Remote Code Execution

An unauthenticated stack-based buffer overflow vulnerability exists in the HTTP API endpoint /cgi-bin/api.values.get. A remote attacker can leverage this vulnerability to achieve unauthenticated remote code execution RCE with root privileges on a target device. The vulnerability affects all six...

Anthropic Claims Chinese AI Firms ‘Distilled’ Claude to Train Their Models

Anthropic claims Chinese AI firms distilled Claude to train rival AI models, raising concerns about model extraction, security risks, and AI distillation abuse...

Analysis of LLMs against Prompt Injection and Jailbreak Attacks

Large Language Models LLMs are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same time, LLMs are vulnerable to prompt-based attacks. Thus,...

AdapTools: Adaptive Tool-Based Indirect Prompt Injection Attacks on Agentic LLMs

The integration of external data services e.g., Model Context Protocol, MCP has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical security vulnerabilities, particularly indirect prompt injection IPI attacks...

📄 GrandStream GXP1600 Unauthenticated Remote Code Execution

An unauthenticated stack-based buffer overflow vulnerability exists in the HTTP API endpoint /cgi-bin/api.values.get. A remote attacker can leverage this vulnerability to achieve unauthenticated remote code execution RCE with root privileges on a target device. The vulnerability affects all six...

CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents

LLM-based code interpreter agents are increasingly deployed in critical workflows, yet their robustness against risks introduced by their code execution capabilities remains underexplored. Existing benchmarks are limited to static datasets or simulated environments, failing to capture the securit...

SafePickle: Robust and Generic ML Detection of Malicious Pickle-Based ML Models

Model repositories such as Hugging Face increasingly distribute machine learning artifacts serialized with Python's pickle format, exposing users to remote code execution RCE risks during model loading. Recent defenses, such as PickleBall, rely on per-library policy synthesis that requires comple...

An Explainable Memory Forensics Approach for Malware Analysis

Memory forensics is an effective methodology for analyzing living-off-the-land malware, including threats that employ evasion, obfuscation, anti-analysis, and steganographic techniques. By capturing volatile system state, memory analysis enables the recovery of transient artifacts such as decrypt...

LLM-Enabled Applications Require System-Level Threat Monitoring

LLM-enabled applications are rapidly reshaping the software ecosystem by using large language models as core reasoning components for complex task execution. This paradigm shift, however, introduces fundamentally new reliability challenges and significantly expands the security attack surface, du...

CVE-2026-20137

In Splunk Enterprise versions below 10.2.0, 10.0.3, 9.4.5, 9.3.7, and 9.2.9, and Splunk Cloud Platform versions below 10.1.2507.0, 10.0.2503.9, 9.3.2411.112, and 9.3.2408.122, a low-privileged user who does not hold the "admin" or "power" Splunk roles could bypass the SPL safeguards for risky...

TFL: Targeted Bit-Flip Attack on Large Language Model

Large language models LLMs are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks. Recent studies have shown that bit-flip attacks BFAs, which exploit computer main memory i.e., DRAM vulnerabilitie...

Would You Click ‘Accept’? Automatically detecting malicious Azure OAuth applications using LLMs

How Wiz Research automates detection of emerging malicious Azure app and consent phishing campaigns...

Grandstream GXP series 安全漏洞

The Grandstream GXP series is a series of IP phones produced by the American company Grandstream. There are security vulnerabilities in the Grandstream GXP series. These vulnerabilities stem from an unauthenticated, stack-based buffer overflow vulnerability in the /cgi-bin/api.values.get HTTP API...

PT-2026-20432

Name of the Vulnerable Software and Affected Versions: Grandstream GXP1610, GXP1615, GXP1620, GXP1625, GXP1628, and GXP1630 versions prior to 1.0.7.81. Description: A critical unauthenticated stack-based buffer overflow vulnerability exists in the HTTP API endpoint /cgi-bin/api.values.get. This...