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...

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...

SMT

Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces Introduction This repository contains the official implementation of our paper: Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces If you find this repository useful for your...

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...

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...

CLEANSTART-2026-MX59138 Calling Decoder

Security vulnerability affects the argo-workflows package. Calling Decoder...

CVE-2026-47738 liboqs: Uninitialized function-pointer dereference in OQS_KEM_encaps_derand for NTRU KEMs

liboqs is a C-language cryptographic library that provides implementations of post-quantum cryptography algorithms. Prior to 0.16.0, OQSKEMencapsderand can dereference an uninitialized encapsderand function pointer when called on NTRU-HPS-2048-509, NTRU-HPS-2048-677, NTRU-HPS-4096-821,...

CLEANSTART-2025-XP66844 Calling Buffer

CVE-2018-7167 affects multiple packages. Calling Buffer. See references for individual vulnerability details...

CLEANSTART-2026-RR59583 Calling Decoder

Security vulnerability affects the argo-workflows package. Calling Decoder...

CLEANSTART-2026-GA63929 Calling Decoder

CVE-2024-34156 affects multiple packages. Calling Decoder. See references for individual vulnerability details...

Signal bug could let someone keep listening after you hang up

A recently disclosed flaw in Signal’s calling software could allow another participant to keep hearing you after you hang up. The vulnerability, tracked as CVE-2026-113380 CVSS score 9.3 out of 10, affects RingRTC versions earlier than 2.72.0. RingRTC is the open-source library behind Signal’s...

CLEANSTART-2026-JF88301 Calling Buffer

Security vulnerability affects the nodejs-24 package. Calling Buffer...

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...