GO-2026-4771 CVE-2026-33815 in github.com/jackc/pgx

Memory-safety vulnerability in github.com/jackc/pgx/v5...

GO-2026-4806 Authorization bypasses in multiple APIs in go.etcd.io/etcd

Authorization bypasses in multiple APIs in go.etcd.io/etcd...

EUVD-2026-19671

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, he superbooga and superboogav2 RAG extensions fetch user-supplied URLs via requests.get with zero validation — no scheme check, no IP filtering, no hostname allowlist. An attacker can access clo...

CVE-2026-5372 runZero Platform SQL injection in saved queries

An issue that allowed a SQL injection attack vector related to saved queries introduced in version 4.0.260123.0. This is an instance of CWE-89: Improper Neutralization of Special Elements used in an SQL Command 'SQL Injection', and has an estimated CVSS score of...

CVE-2026-5627 Path Traversal in mintplex-labs/anything-llm

A path traversal vulnerability exists in mintplex-labs/anything-llm versions up to and including 1.9.1, within the AgentFlows component. The vulnerability arises from improper handling of user input in the loadFlow and deleteFlow methods in server/utils/agentFlows/index.js. Specifically, the...

RLSA-2026:5942 Important: golang security update

The golang packages provide the Go programming language compiler. Security Fixes: cmd/go: cmd/go: Arbitrary file write via malicious pkg-config directive CVE-2025-61731 net/url: Incorrect parsing of IPv6 host literals in net/url CVE-2026-25679 For more details about the security issues, including...

Benchmarking-Agent-Architectures

Benchmarking Agent Architectures for LLM-Based Exploit Gener...

CVE-2026-5620

A vulnerability has been found in itsourcecode Construction Management System 1.0. Affected is an unknown function of the file /borrowedequipreport.php of the component Parameter Handler. The manipulation of the argument Home leads to sql injection. It is possible to initiate the attack remotely...

CVE-2026-5719

A flaw has been found in itsourcecode Construction Management System 1.0. This affects an unknown function of the file /borrowedtool.php. Executing a manipulation of the argument code can lead to sql injection. It is possible to launch the attack remotely. The exploit has been published and may b...

Guiding Symbolic Execution with Static Analysis and LLMs for Vulnerability Discovery

Symbolic execution detects vulnerabilities with precision, but applying it to large codebases requires harnesses that set up symbolic state, model dependencies, and specify assertions. Writing these harnesses has traditionally been a manual process requiring expert knowledge, which significantly...

SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills

OpenClaw's ClawHub marketplace hosts over 13,000 community-contributed agent skills, and between 13% and 26% of them contain security vulnerabilities according to recent audits. Regex scanners miss obfuscated payloads; formal static analyzers cannot read the natural language instructions in...

From Incomplete Architecture to Quantified Risk: Multimodal LLM-Driven Security Assessment for Cyber-Physical Systems

Cyber-physical systems often contend with incomplete architectural documentation or outdated information resulting from legacy technologies, knowledge management gaps, and the complexity of integrating diverse subsystems over extended operational lifecycles. This architectural incompleteness...

Towards the Development of an LLM-Based Methodology for Automated Security Profiling in Compliance with Ukrainian Cybersecurity Regulations

In recent years, the pace of development of information technology in various areas has increased drastically, forcing cybersecurity specialists to constantly review existing processes in order to prevent unauthorized access to confidential information. Using Ukraine as a primary case study, this...

Google Go 安全漏洞

Google Go is a static, strongly typed, compiled, concurrent programming language with garbage collection features from the American company Google. There is a security vulnerability in Google Go, which stems from memory security issues...

Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents

With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team methods mostly rely on modifying user prompts, which lack adaptability to new data and may impact the agent's performance. To address the challenge,...

Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing

The rapid advancement of Large Language Models LLMs has created new opportunities for Automated Penetration Testing AutoPT, spawning numerous frameworks aimed at achieving end-to-end autonomous attacks. However, despite the proliferation of related studies, existing research generally lacks...

Swiss-Bench 003: Evaluating LLM Reliability and Adversarial Security for Swiss Regulatory Contexts

The deployment of large language models LLMs in Swiss financial and regulatory contexts demands empirical evidence of both production reliability and adversarial security, dimensions not jointly operationalized in existing Swiss-focused evaluation frameworks. This paper introduces Swiss-Bench 003...

MA-IDS: Multi-Agent RAG Framework for IoT Network Intrusion Detection with an Experience Library

Network Intrusion Detection Systems NIDS face important limitations. Signature-based methods are effective for known attack patterns, but they struggle to detect zero-day attacks and often miss modified variants of previously known attacks, while many machine learning approaches offer limited...

runZero Platform 安全漏洞

runZero Platform is an asset discovery and attack surface management platform developed by the US company runZero. There is a security vulnerability in the version 4.0.260123.0 of runZero Platform, which stems from improper handling of special elements related to query storage. This vulnerability...

PT-2026-30798

The SQL Chart Builder WordPress plugin before 2.3.8 does not properly escape user input as it is concatened to SQL queries, making it possible for attackers to conduct SQL Injection attacks against the dynamic filter functionality...