LLM-Based Penetration Testing in the Presence of Honeypots

Large language model LLM agents are increasingly employed for offensive cybersecurity tasks such as automated vulnerability discovery, reconnaissance, and penetration testing. This new capability also threatens one of the defender's most valuable tools: deception. Traditional honeypots rely on...

Staying on the Attack Path: Structured State for Long-Horizon Automated Penetration Testing

Large language model LLM based agents are increasingly applied to cybersecurity tasks such as vulnerability discovery and automated penetration testing. On long-horizon security tasks, however, such agents remain limited by context forgetting and intent drift: early critical facts and causal...

Benchmarking LLMs for Threat Level Determination

The fast progress of large language models LLMs opens new opportunities in the management of cyber threat intelligence, but their reliability for operational tasks remains unclear. In this work, we benchmark LLMs on the task of threat level determination. First, we construct a curated dataset...

VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities

The software supply chain has become an increasingly exposed attack surface because of its reliance on intricate yet fragile dependencies. Existing defenses such as GitHub Dependabot often raise many false alerts because their coarse-grained matching cannot determine whether a vulnerable dependen...

AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories

LLM agents complete tasks by issuing sequences of tool calls, and every observation they read is a channel through which an indirect prompt injection can enter. A successful injection has a characteristic shape when the trajectory is read in order: a benign prefix gives way to actions that serve...

Characterizing Contention-Induced Reliability Collapse in KV-Cache Timing Side Channels for Multi-Tenant LLM Serving

Shared key--value KV cache reuse improves large language model LLM serving, but it can also create a timing side channel that reveals whether a prefix is already cached. Previous work shows that such attacks are possible, but their reliability under realistic multi-tenant contention is less...

AURA-Eval: Evaluation Framework for Acting under Risk Awareness in LLM Agent Trajectories

LLM agents operate in workflows where unsafe actions can have real consequences. Existing safety evaluations often reduce behavior to a single score, obscuring risk recognition, pre-action detection, and safe task completion when a safe solution exists. We introduce AURA-Eval, a framework combini...

exploitgym-unified

ExploitGym Unified Runner - 898 instâncias + Dashboard Live R...

monty v0.0.22

Monty A minimal, secure Python interpreter written in Rust for use by AI. Experimental - This project is still in development, and not ready for prime time. A minimal, secure Python interpreter written in Rust for use by AI. Monty avoids the cost, latency, complexity and general faff of using a...

SUSE CVE-2026-64859

New API is a large language mode LLM gateway and artificial intelligence AI asset management system. Prior to 1.0.0-rc.7, the admin user list and user lookup APIs, including GET /api/user/, return User.AccessToken as accesstoken because User model objects are serialized after queries use...

SUSE CVE-2026-64865

New API is a large language mode LLM gateway and artificial intelligence AI asset management system. Prior to 1.0.0-rc.16, repeated PUT /api/user/self requests that update language or sidebarmodules can race relay billing because controller/user.go calls User.Update and updateUserCache performs a...

SUSE CVE-2026-64866

New API is a large language mode LLM gateway and artificial intelligence AI asset management system. From 0.9.1.3 until 1.0.0-rc.7, AdminResetPasskey in controller/passkey.go lacks the canManageTargetRole authorization check for DELETE /api/user/:id/resetpasskey, allowing a lower-privileged...

SUSE CVE-2026-64868

New API is a large language mode LLM gateway and artificial intelligence AI asset management system. Prior to 1.0.0-rc.11, POST /api/stripe/webhook, POST /api/creem/webhook, and POST /api/waffo/webhook read and log full request bodies before signature validation in router/api-router.go and the...

SUSE CVE-2026-71479

New API is a large language mode LLM gateway and artificial intelligence AI asset management system. Prior to 1.0.0-rc.18, user-controlled image n, video seconds and duration, maxtokens, maxcompletiontokens, maxOutputTokens, audio duration, and billing-expression quantities can overflow conversio...

GHSA-M4RF-3FR8-XWX3 vulnerabilities

Vulnerabilities for packages: nemo, open-webui...

NPM: CodeWhale: exec_shell_interact sends LLM-controlled input to a running shell without an approval prompt (privilege escalation)

NPM: CodeWhale: execshellinteract sends LLM-controlled input to a running shell without an approval prompt privilege escalation vulnerability discovered by ? in WordPress Npm deepseek-tui versions = 0.3.10, 0.8.41...

GHSA-G29H-PFMP-QP9R CodeWhale: exec_shell_interact sends LLM-controlled input to a running shell without an approval prompt (privilege escalation)

Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 57f3c89471e27ac4032d9791f6885e5d4408c381. Users should upgrade to 0.8.64 or later. The original reporter analysis is...

NPM: CodeWhale: exec_shell_interact sends LLM-controlled input to a running shell without an approval prompt (privilege escalation)

NPM: CodeWhale: execshellinteract sends LLM-controlled input to a running shell without an approval prompt privilege escalation vulnerability discovered by ? in WordPress Npm codewhale versions = 0.8.41, 0.8.64...

EUVD-2026-60964

CodeWhale: execshellinteract sends LLM-controlled input to a running shell without an approval prompt privilege escalation...

CodeWhale: exec_shell_interact sends LLM-controlled input to a running shell without an approval prompt (privilege escalation)

Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 57f3c89471e27ac4032d9791f6885e5d4408c381. Users should upgrade to 0.8.64 or later. The original reporter analysis is...