SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents

Autonomous LLM agents increasingly operate in stateful environments where they access tools, files, memory, and external services. While such capabilities enable complex real-world workflows, they also introduce security risks that are difficult to capture with existing evaluations. Current agent...

Malicious Package

Overview Sicoob-Cooperativa.Sicoob.ConvenioPagamentos is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that...

Malicious Package

Overview Sicoob-Cooperativa.Sicoob.Auth is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and thi...

Malicious Package

Overview Sicoob-Cooperativa.Sicoob.Poupanca is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and...

ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree

Agent skills extend AI agents with reusable instructions, tools, scripts, references, and workflows, establishing a security boundary distinct from both model safety and traditional package-malware detection. ClawHub Security Signals is a sanitized dataset of 67,453 latest public OpenClaw skill...

web-application-security-testing-tool

web-application-security-testing-tool A Python-based Web Appli...

How to Compare the Security of Code Written by Humans to LLM-Generated Code

Large language models LLMs are rapidly transforming how software is created and maintained. Comparing LLM-generated code against human-written standards is essential to determine whether these new tools uphold or erode the security baselines established by professional developers. Yet, we lack a...

Automatically Attacking Software Reverse Engineering AI Agents

Software tools for reverse engineering executable binary files, such as Ghidra, enable malware analysts to safely conduct robust static analysis without having access to original source code. Coupled with the analytic power of large language models LLM, agentic systems enabled with tools, such as...

CVE-2026-9582

A security flaw has been discovered in SourceCodester CET Automated Grading System with AI Predictive Analytics 1.0. This affects an unknown function. Performing a manipulation results in cross-site request forgery. The attack is possible to be carried out remotely. The exploit has been released ...

CVE-2026-9583

The CVE-2026-9583 entry details an information-exposure vulnerability in SourceCodester CET Automated Grading System with AI Predictive Analytics 1.0. It affects the SQL Handler component (file /index.php) where manipulation can cause information disclosure via error messages. The issue is exploi...

CVE-2026-9583

A weakness has been identified in SourceCodester CET Automated Grading System with AI Predictive Analytics 1.0. This impacts an unknown function of the file /index.php of the component SQL Handler. Executing a manipulation can lead to information exposure through error message. The attack may be...

CVE-2026-9582 SourceCodester CET Automated Grading System with AI Predictive Analytics cross-site request forgery

A security flaw has been discovered in SourceCodester CET Automated Grading System with AI Predictive Analytics 1.0. This affects an unknown function. Performing a manipulation results in cross-site request forgery. The attack is possible to be carried out remotely. The exploit has been released ...

EUVD-2026-31996

A security flaw has been discovered in SourceCodester CET Automated Grading System with AI Predictive Analytics 1.0. This affects an unknown function. Performing a manipulation results in cross-site request forgery. The attack is possible to be carried out remotely. The exploit has been released ...

AI_AutoExploitGeneration

🎯 AI-POWERED AUTOMATED EXPLOIT GENERATION AEG SYSTEM Vers...

PT-2026-46327

Name of the Vulnerable Software and Affected Versions AirSupply versions prior to 2.0.1 Description An unauthenticated Local File Inclusion LFI exists, which allows an attacker to read files from the local file system without requiring authentication. Recommendations Update to a version newer tha...

PT-2026-46331

Name of the Vulnerable Software and Affected Versions MaxiNet versions prior to 1.2.11 Description An unauthenticated Local File Inclusion allows an attacker to read files from the local file system without requiring authentication. Recommendations Update to a version newer than 1.2.10...

PT-2026-46320

Name of the Vulnerable Software and Affected Versions Geya versions prior to 1.16 Description An unauthenticated Local File Inclusion LFI exists, which allows an attacker to include and read local files on the server without requiring authentication. Recommendations Update to a version later than...

PT-2026-46325

Name of the Vulnerable Software and Affected Versions Hot Coffee versions prior to 1.8 Description An unauthenticated PHP Object Injection issue exists. PHP Object Injection occurs when an application unserialize user-supplied input without proper validation, potentially allowing an attacker to...

PT-2026-46324

Name of the Vulnerable Software and Affected Versions Rosaleen versions prior to 2.9 Description An unauthenticated Local File Inclusion LFI exists, which allows an attacker to include files from the local file system without requiring authentication. Recommendations Update to a version newer tha...

CVE-2026-9583: Generation of Error Message Containing Sensitive Information

A weakness has been identified in SourceCodester CET Automated Grading System with AI Predictive Analytics 1.0. This impacts an unknown function of the file /index.php of the component SQL Handler. Executing a manipulation can lead to information exposure through error message. The attack may be...