Benchmarking-Agent-Architectures

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

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Cyber-physical systems often contend with incomplete architectural documentation or outdated information resulting from legacy technologies, knowledge management gaps, and the complexity of integrating diverse subsystems over extended operational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

CritBench: A Framework for Evaluating Cybersecurity Capabilities of Large Language Models in IEC 61850 Digital Substation Environments

The advancement of Large Language Models LLMs has raised concerns regarding their dual-use potential in cybersecurity. Existing evaluation frameworks overwhelmingly focus on Information Technology IT environments, failing to capture the constraints, and specialized protocols of Operational...

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...

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...

WebSP-Eval: Evaluating Web Agents on Website Security and Privacy Tasks

Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluate general-purpose performancee.g., WebArena or safety against malicious actionse.g., SafeArena, no existing framework assesses an agent's ability to...

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw

OpenClaw, the most widely deployed personal AI agent in early 2026, operates with full local system access and integrates with sensitive services such as Gmail, Stripe, and the filesystem. While these broad privileges enable high levels of automation and powerful personalization, they also expose...

CVE-2019-25687

Pegasus CMS 1.0 contains a remote code execution vulnerability in the extrafields.php plugin that allows unauthenticated attackers to execute arbitrary commands by exploiting unsafe eval functionality. Attackers can send POST requests to the submit.php endpoint with malicious PHP code in the acti...

CVE-2019-25687 Pegasus CMS 1.0 Remote Code Execution via extra_fields.php

Pegasus CMS 1.0 contains a remote code execution vulnerability in the extrafields.php plugin that allows unauthenticated attackers to execute arbitrary commands by exploiting unsafe eval functionality. Attackers can send POST requests to the submit.php endpoint with malicious PHP code in the acti...

CVE-2026-5594 premAI-io premsql followup.py eval code injection

A weakness has been identified in premAI-io premsql up to 0.2.1. Affected is the function eval of the file premsql/agents/baseline/workers/followup.py. This manipulation of the argument result causes code injection. The attack is possible to be carried out remotely. The exploit has been made...

VulnCheck KEV: CVE-2025-59528

Flowise is a drag & drop user interface to build a customized large language model flow. In version 3.0.5, Flowise is vulnerable to remote code execution. The CustomMCP node allows users to input configuration settings for connecting to an external MCP server. This node parses the user-provided...

Towards Unveiling Vulnerabilities of Large Reasoning Models in Machine Unlearning

Large language models LLMs possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models LRMs, which provide explicit multi-step reasoning traces. On the other hand, the growing need for the right to be forgotte...

PT-2026-30495

Pegasus CMS 1.0 contains a remote code execution vulnerability in the extra fields.php plugin that allows unauthenticated attackers to execute arbitrary commands by exploiting unsafe eval functionality. Attackers can send POST requests to the submit.php endpoint with malicious PHP code in the...

Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode

Claude Code's auto mode is the first deployed permission system for AI coding agents, using a two-stage transcript classifier to gate dangerous tool calls. Anthropic reports a 0.4% false positive rate and 17% false negative rate on production traffic. We present the first independent evaluation o...

CVE-2026-35002

Agno versions prior to 2.3.24 contain an arbitrary code execution vulnerability in the model execution component that allows attackers to execute arbitrary Python code by manipulating the fieldtype parameter passed to eval. Attackers can influence the fieldtype value in a FunctionCall to achieve...

CVE-2026-33691 OWASP CRS: Whitespace padding in filenames bypasses file upload extension checks

The OWASP core rule set CRS is a set of generic attack detection rules for use with compatible web application firewalls. Prior to versions 3.3.9 and 4.25.0, a bypass was identified in OWASP CRS that allows uploading files with dangerous extensions .php, .phar, .jsp, .jspx by inserting whitespace...

Exploit for Path Traversal in Publiccms

amihit Am I Hit? -- CVE Impact Analyzer !Gohttps://i...

Seclens: Role-Specific Evaluation of LLM'S for Security Vulnerablity Detection

Existing benchmarks for LLM-based vulnerability detection compress model performance into a single metric, which fails to reflect the distinct priorities of different stakeholders. For example, a CISO may emphasize high recall of critical vulnerabilities, an engineering leader may prioritize...

BIT-GRAFANA-2026-27880 OpenFeature evaluation API reads input data with no bounds

The OpenFeature feature toggle evaluation endpoint reads unbounded values into memory, which can cause out-of-memory crashes...

AutoEG: Exploiting Known Third-Party Vulnerabilities in Black-Box Web Applications

Large-scale web applications are widely deployed with complex third-party components, inheriting security risks arising from component vulnerabilities. Security assessment is therefore required to determine whether such known vulnerabilities remain practically exploitable in real applications...