Runaway Reaction: When Benign Skills Compose into Malicious Behavior

Agent skills package task-specific knowledge and procedures that can be composed to support complex agent tasks, while public marketplaces provide a growing pool of reusable skills. Existing security vetting, however, largely evaluates skills in isolation, leaving composition-induced risks...

Exploring Privacy Leakage and Data Disclosure Violations in the MacOS Application Ecosystem

The systematic and excessive data collection practices of tech companies have rendered online privacy both a necessity and a sought-after commodity. However, while the privacy risks of the web, mobile, and IoT ecosystems have been extensively examined, desktop environments have been largely...

ToolGuardian: Declarative Security for AI Agent-Tool Interactions

LLM agents increasingly rely on external tools, expanding capability while creating a new security boundary: third-party tools may appear benign at the interface level while embedding unsafe behavior in implementation. Existing defenses rely on weak metadata, collapse characterization and policy...

New Webinar: Closing the Approval Gap in AI-Era Ad Tech

A single approved marketing tag can quietly load fourth-party code your security team has never seen, granting full access to your forms, customer data, and checkout pages. This on-demand webinar reveals how this Approval Gap forms, and gives your team the blueprint to close it before an auditor,...

PhantomSkill: Malicious Code Injection in Agent Skill Ecosystems

Agent skills allow LLM-based coding agents to acquire domain-specific capabilities from third-party packages, but they also introduce a new supply-chain attack surface. We present PhantomSkill, an attack framework that hides malicious behavior in a skill's auxiliary resources rather than in its...

SkillVetBench: LLM-As-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills

Open-source LLM agent ecosystems are growing rapidly, yet the security of community-contributed skills - modular tool definitions that extend agent capabilities - remains largely unvetted. The gap we fill: existing scanners operate at the code layer and are structurally blind to instruction-layer...

Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems

Open agent platforms allow community contributors to publish reusable skills that agents can invoke at runtime. This extensibility also creates a supply-chain risk: malicious contributors can hide harmful behavior inside skills that appear benign under superficial inspection. However, existing...

Open VSX Bug Let Malicious VS Code Extensions Bypass Pre-Publish Security Checks

Cybersecurity researchers have disclosed details of a now-patched bug impacting Open VSX's pre-publish scanning pipeline to cause the tool to allow a malicious Microsoft Visual Studio Code VS Code extension to pass the vetting process and go live in the registry. "The pipeline had a single boolea...

Eclipse Foundation Mandates Pre-Publish Security Checks for Open VSX Extensions

The Eclipse Foundation, which maintains the Open VSX Registry, has announced plans to enforce security checks before Microsoft Visual Studio Code VS Code extensions are published to the open-source repository to combat supply chain threats. The move marks a shift from a reactive to a proactive...

PT-2025-51355

Name of the Vulnerable Software and Affected Versions Fickling versions prior to 0.1.6 Description Fickling, a Python pickling decompiler and static analyzer, contained a bypass related to missing unsafe module imports. Specifically, the pty module was not included in the block list, leading to...

Securing the Model Context Protocol: Defending LLMs against Tool Poisoning and Adversarial Attacks

The Model Context Protocol MCP enables Large Language Models to integrate external tools through structured descriptors, increasing autonomy in decision-making, task execution, and multi-agent workflows. However, this autonomy creates a largely overlooked security gap. Existing defenses focus on...

Jasper Sleet: North Korean remote IT workers’ evolving tactics to infiltrate organizations

Since 2024, Microsoft Threat Intelligence has observed remote information technology IT workers deployed by North Korea leveraging AI to improve the scale and sophistication of their operations, steal data, and generate revenue for the Democratic People’s Republic of Korea DPRK. Among the changes...

HackerOne: Possible PII Disclosure via Advanced Vetting Process - ██████

Possible PII disclosure was identified in the HackerOne Advanced Vetting process. Unauthorized users were able to download a CSV file containing the names, usernames, and other personal details of users who had accepted the Advanced Vetting terms. The issue was observed in a sandboxed program, bu...

Scammers Use Fake Ledger App on Microsoft Store to Steal $800,000 in Crypto

By Deeba Ahmed After a surge of malware on the Google Play Store, is Microsoft also failing to properly vet apps for malware? This is a post from HackRead.com Read the original post: Scammers Use Fake Ledger App on Microsoft Store to Steal $800,000 in Crypto...

Ubuntu 16.04 LTS / 18.04 LTS : Firefox vulnerability (USN-4032-1)

The remote Ubuntu 16.04 LTS / 18.04 LTS host has packages installed that are affected by a vulnerability as referenced in the USN-4032-1 advisory. It was discovered that a sandboxed child process could open arbitrary web content in the parent process via the Prompt:Open IPC message. When combined...

Any of the role setter , nominee Vetter should not be a council (cohort) member.

Lines of code Vulnerability details Impact The privileged cohort membercouncil member can influence the member addition, removal, rotating the nominee and excluding the nominee. The function of election can be rigged, arbitrary proposals can be passed. This is easy by the council member who has...

A proxyjacking campaign is looking for vulnerable SSH servers

A researcher at Akamai has posted a blog about a worrying new trend--proxyjacking--where criminals sell your bandwidth to a third-party proxy service. To understand how proxyjacking works, well need to explain a few things. There are several legitimate services that pay users to share their surpl...

The MSP playbook on deciphering tech promises and shaping security culture

The in-person cybersecurity conference has returned. More than two years after Covid-19 pushed nearly every in-person event online, cybersecurity has returned to the exhibition hall. In San Francisco earlier this year, thousands of cybersecurity professionals walked the halls of Moscone Center at...

Mageia: Security Advisory (MGASA-2020-0009)

The remote host is missing an update for the SPDX-FileCopyrightText: 2022 Greenbone AG Some text descriptions might be excerpted from a referenced sources, and are Copyright C by the respective right holders. SPDX-License-Identifier: GPL-2.0-only ifdescription...

CISA Releases Guidance on Protecting Organization-Run Social Media Accounts

CISA has released Capacity Enhancement Guide CEG: Social Media Account Protection, which details ways to protect the security of organization-run social media accounts. Malicious cyber actors that successfully compromise social media accounts—including accounts used by federal agencies—could spre...