EUVD-2026-29509

The superduper project thru v0.10.0 contains a critical remote code execution vulnerability in its query parsing component. The parseoppart function in query.py uses the unsafe eval function to dynamically evaluate user-supplied query operands without proper sanitization or restriction. Although...

EUVD-2026-29362

Due to missing authorization check in SAP Strategic Enterprise Management Scorecard Wizard in Business Server Pages, an authenticated attacker could access information that they are otherwise unauthorized to view. This vulnerability also enables the attacker to change the default settings and...

CVE-2026-40132

Due to missing authorization check in SAP Strategic Enterprise Management Scorecard Wizard in Business Server Pages, an authenticated attacker could access information that they are otherwise unauthorized to view. This vulnerability also enables the attacker to change the default settings and...

CVE-2026-40132

CVE-2026-40132 concerns SAP Strategic Enterprise Management (Scorecard Wizard in BSP). The vulnerability stems from a missing authorization check, allowing an authenticated attacker to view information they should not access and to alter default settings and value fields, which could mislead risk...

CVE-2026-40132 Missing Authorization Check in SAP Strategic Enterprise Management (BSP application Balanced Scorecard Wizard)

Due to missing authorization check in SAP Strategic Enterprise Management Scorecard Wizard in Business Server Pages, an authenticated attacker could access information that they are otherwise unauthorized to view. This vulnerability also enables the attacker to change the default settings and...

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for predefined goals such as capture-the-flag, remote code...

superduper 安全漏洞

Superduper is an open-source database integration AI proxy and application building tool developed by superduper.io. Versions of Superduper prior to v0.10.0 contained security vulnerabilities. These vulnerabilities stemmed from the Parseoppart function in the query parsing component, which used t...

Adversarial Robustness Toolbox 安全漏洞

Adversarial Robustness Toolbox is an open-source machine learning security defense and evaluation tool developed by Trusted-AI. Versions of Adversarial Robustness Toolbox 1.20.1 and earlier contained security vulnerabilities. These vulnerabilities stemmed from the robustness evaluation function i...

CTFusion: A CTF-Based Benchmark for LLM Agent Evaluation

Recent advances in Large Language Models LLMs have enabled agentic systems for complex, multi-step tasks; cybersecurity is emerging as a prominent application. To evaluate such agents, researchers widely adopt Capture The Flag CTF benchmarks. However, current CTF benchmarks reuse existing...

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces

Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environments. However, this modularity introduces attack surfaces that are largely missed by existing safety evaluations: eve...

PT-2026-40117

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a command-line argument injection vulnerability in its Kubeflow component robustness evaluation fgsm pytorch.py. The script uses the unsafe eval function to parse string values provided via the --clip values and --input shape command-lin...

CVE-2026-31225

The superduper project thru v0.10.0 contains a critical remote code execution vulnerability in its query parsing component. The parseoppart function in query.py uses the unsafe eval function to dynamically evaluate user-supplied query operands without proper sanitization or restriction. Although...

CVE-2026-31228

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a remote code execution vulnerability in its Kubeflow component. The robustness evaluation function for PyTorch models uses the unsafe eval function to dynamically evaluate user-supplied strings for the LossFn and Optimizer parameters...

PT-2026-40066

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a remote code execution vulnerability in its Kubeflow component. The robustness evaluation function for PyTorch models uses the unsafe eval function to dynamically evaluate user-supplied strings for the LossFn and Optimizer parameters...

CVE-2026-31228

The connected documents confirm a vulnerability in the Adversarial Robustness Toolbox (ART) up to version 1.20.1, specifically in its Kubeflow component. The root cause is that the robustness evaluation function for PyTorch models uses Python’s unsafe eval() to dynamically evaluate user-supplied ...

LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments

The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous OS-level operations with irreversible consequences. Existing...

PT-2026-41191

Name of the Vulnerable Software and Affected Versions Open WebUI versions prior to 0.9.5 Description An authenticated attacker can perform mass assignment via the 'POST /api/v1/evaluations/feedback' endpoint. This is possible because the FeedbackForm uses a configuration that allows extra fields,...

MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate monitor performance. We identify three challenges with current red-teaming. First, mode collapse in attack generation,...

Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning

We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use protocols, causing incorrect conclusions through correct reasoning. Unlike prompt injection, Oracle Poisoning manipulates the data agents reason ove...

Remote Code Execution (RCE)

dedoc/scramble is vulnerable to Remote Code Execution RCE. The vulnerability is due to unsafe evaluation of user-controlled input during documentation generation, which allows an attacker to execute arbitrary PHP code in the application context...