run-gemini-cli

run-gemini-cli Overview run-gemini-cli is a GitHub Action that integrates Gemini into your development workflow via the Gemini CLI. It acts both as an autonomous agent for critical routine coding tasks, and an on-demand collaborator you can quickly delegate work to. Use it to perform GitHub pull...

binja_arch_ref

binjaarchref A simple Binary Ninja plugin to display a cheat sheet with information about the current architecture Origins This project is a product of NCC Group's 2017 summer internship program. Further updates will be tracked athttps://github.com/ehennenfent/binjaarchref. NCC Group is not...

ZeroHVCI

ZeroHVCI - Defeating HVCI without admin privileges or a kernel driver ZeroHVCI accomplishes arbitrary kernel read/writes/function calling in Hypervisor-Protected Code Integrity HVCI protected environments calling without admin permissions or kernel drivers. Features Full non-privileged kernel...

llm-agent-testbed

🛡️ LLM Agent Security Testbed Empirical Vulnerability & Defense Harness for Tool-Calling LLM Agents A disciplined security testbed testing whether tool-equipped LLM agents can be manipulated into unauthorized data exfiltration via prompt injection, role-claim social engineering, and confused-deput...

India Mandates Registered Caller Name Display on 4G and Newer Networks From November 1

The Indian government has directed telecom service providers TSPs in the country to mandatorily display callers' registered names along with their numbers for incoming calls starting November 1, 2026, in an effort to help people identify calls from unknown numbers and tackle spam or fraudulent...

CVE-2026-94584: Concurrent Execution using Shared Resource with Improper Synchronization

A race condition and thread-safety vulnerability exists in the web management daemon of Brocade Fabric OS versions before 10.0.1. When handling user authentication requests across a multi-threaded execution pool, this race condition causes PAM modules to process stale or incorrect client IP...

OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents

LLM agents with tool-calling capabilities can access external services and private user data, but they may retrieve more information than a user's request explicitly requires. We study this behavior in structured tool-calling agents and term it proactive over-authorization. This setting differs...

Persistent Billable State: Denial-Of-Wallet Attacks and Defenses in Tool-Calling LLM Agents

Multi-step tool-calling LLM agents rely on host runtimes to preserve state across turns. When a runtime carries an external tool return into later model inputs, providers meter it again. An admitted malicious or compromised tool can thereby convert untrusted data into recurring victim-billed...

Allocation of Resources Without Limits or Throttling

Overview Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling due to the absence of a total timeout in the remote policy fetch process. An attacker can cause the application to hang indefinitely by making a server respond extremely slowly, there...

CVE-2026-91867

When Neethi fetches a remote policy reference, it only limits the time per read, not the whole transfer, so a server that trickles bytes slowly can keep the fetch alive indefinitely and tie up the calling thread denial of service. Users are recommended to upgrade to version 3.2.4, which fixes thi...

aixsec-x

AIXSEC-X — AI Web Exploitation Assistant local LLM, Kali Linu...

Measuring and Exploiting Implicit Trust in LLM Tool-Calling Pipelines

The Model Context Protocol MCP enables LLMs to invoke external tools, but every tool interaction exposes the model to attacker-controlled text through multiple input channels tool descriptions, tool results, sampling messages that share a single context window without privilege separation. In thi...

CVE-2026-59318

In Spring AI's tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked, potentially leading to privilege...

EUVD-2026-63933

In Spring AI's tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked, potentially leading to privilege...

CVE-2026-59318

In Spring AI's tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked, potentially leading to privilege...

PT-2026-79377

Name of the Vulnerable Software and Affected Versions Spring AI version 2.0.0 Spring AI versions 1.1.0 through 1.1.8 Spring AI versions 1.0.0 through 1.0.9 Description In the tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced during...

CVE-2026-59318: Incorrect Authorization

In Spring AI's tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked, potentially leading to privilege...

Black Hat Europe 2024 Conference Slides

Black Hat Europe 2024 conference slides for topics Vulnerabilities in the eSIM download protocol, WiFi Calling: Revealing Downgrade Attacks and Not-so-private private Keys, From Pass-the-Hash to Code Execution on Schneider Electric M340 PLCs, CodeCloak: A DRL-Based Method for Mitigating Code...

From Prompt Injection to Web Exploitation: Revisiting Classic Vulnerabilities in LLM-Integrated Applications

Large Language Models are increasingly integrated into web applications through chatbots, tool-calling pipelines, and agentic workflows. In these systems, user input may influence not only generated text, but also backend actions such as database queries, HTTP requests, file operations, template...

PT-2026-67846

Name of the Vulnerable Software and Affected Versions Open WebUI versions 0.8.8 through 0.10.2 Description An issue exists where inline direct model metadata accepts client-supplied knowledge attachments without verifying the caller's read access. This occurs when a client defines a model inline...