AWS API MCP Server Security Policy Bypass via Startup Initialization Failure

SummaryThe AWS API MCP Server is an open source Model Context Protocol MCP server that enables AI assistants to interact with AWS services and resources through AWS CLI commands. It provides programmatic access to manage your AWS infrastructure while maintaining proper security controls. It...

Open WebUI: Arena task endpoints can bypass underlying model access controls

SummaryAn authenticated non-admin user with read access to an arena wrapper model can reach a restricted underlying model through task endpoints such as /api/v1/tasks/moa/completions.The normal chat route resolves arena models before the final chat dispatch and therefore re-checks the selected...

PYSEC-2026-3601 Open WebUI: Arena task endpoints can bypass underlying model access controls

Summary An authenticated non-admin user with read access to an arena wrapper model can reach a restricted underlying model through task endpoints such as /api/v1/tasks/moa/completions. The normal chat route resolves arena models before the final chat dispatch and therefore re-checks the selected...

“Keep going, bro. You’ve got this!” A data-driven look at how adversaries are weaponizing AI

Actor usage of AI is exploding. By analyzing artifacts left behind, Talos has created a detailed analysis of how we are seeing adversaries leverage the technology to include development, force multiplication, and vulnerability research. Based on the evidence Talos gathered, guardrails did not...

DOUBLECUP Uses ClickFix and Cached PNGs to Deliver CountLoader and DeviceManager RAT

A new Russian loader-as-a-service LaaS codenamed DOUBLECUP has been using ClickFix lures as a way to stage malware-laced PNG images in victims' browser cache and ultimately deliver CountLoader and a previously undocumented remote access trojan called DeviceManager. "The first stage drops a...

rev-dep v3.0.0

Rev-dep Capabilities • Installation • Documentation • Exploratory Toolkit • CLI Reference Dependency analysis and optimization toolkit for modern JavaScript and TypeScript codebases. Enforce dependency graph hygiene and remove unused code with a very fast CLI. About 📣 As codebases scale,...

kuri v0.6.0

Kuri 🌰 Install root@kitploit: curl -fsSL https://kuri.trilok.ai/download | sh macOS arm64/x8664 and Linux x8664/arm64. Single binary, no runtime deps. Direct downloads: macOS arm64 · macOS x8664 · Linux x8664 · Linux arm64 Browser automation & web crawling for AI agents. Written in Zig. Zero...

MAL-2026-11516 Malicious code in coldcard-helpers (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 8aea0829143169ee7227c8974c3b42125e95b89387a00ccb2b37d1d7344b041a The package presents itself as a helper for the Coldcard hardware wallet, but its actual behavior is credential and wallet theft. setup.py detects...

Malicious code in coldcard-helpers (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 8aea0829143169ee7227c8974c3b42125e95b89387a00ccb2b37d1d7344b041a The package presents itself as a helper for the Coldcard hardware wallet, but its actual behavior is credential and wallet theft. setup.py detects...

hate_crack v2.25.1

root@kitploit: / | \ / | \ \ | | / \ \ / \ / \ /\ \ \ / | |/ / \ Y // | | \ / \ | | // \ | \ /|| /\ | \ / / // / / / / Installation Installing from source is the only supported path. hatecrack is not distributed on PyPI: pip install hate-crack resolves to a 0.0.0 placeholder that...

Exploit for CVE-2026-21019

--- CVE-2026-21019 – Kubernetes CronJob Suspended Execution...

Echoes in the Digital Abyss: Examining the Bubble Surrounding Security and Privacy Discourse in Social Networks

The dissemination of security and privacy education and guidance has been and still remains a challenge today. Social networks represent a potential avenue for sharing best practices, and experimentally they have been found to be effective at this task. While this appears promising, in the real...

AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection

Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous encounters. In practice, user requests are often underspecified: they describe the desired outcome without fully specifying acceptable behavior. An...

WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks

Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these...

When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills

Persona skills distill personal interaction histories into portable and executable artifacts for downstream agents. While enabling flexible personalization, this process concentrates fragmented personal signals, amplifies their impact through reuse, and challenges defenses designed for individual...

Oracle Linux 7 / 8 : Unbreakable Enterprise kernel (ELSA-2026-500121)

The remote Oracle Linux 7 / 8 host has packages installed that are affected by multiple vulnerabilities as referenced in the ELSA-2026-500121 advisory. - xfs: resample the data fork mapping after cycling ILOCK Darrick J. Wong Orabug: 39776792 CVE-2026-64600 - net/sched: fix pedit partial COW...

DiagChain: A Diagnostic Benchmark for Evaluating LLM Agents on Evidence-Grounded Attack Chain Reconstruction

Large Language Model LLM agents offer a promising approach to attack chain reconstruction by retrieving and interpreting heterogeneous telemetry to infer ordered attacker actions. However, existing benchmarks mainly evaluate final outputs or aggregate accuracy, providing limited insight into how...

Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills

Closed source agent skills may encode proprietary instructions, scripts, constants, and data. Providers may offer their capabilities as services while keeping the underlying packages hidden. Prior work focuses on prompt injection attacks that directly disclose these artifacts, and existing defens...

winfsp v2.2B4

WinFsp · Windows File System Proxy WinFsp enables developers to write their own file systems i.e. "Windows drives" as user mode programs and without any knowledge of Windows kernel programming. It is similar to FUSE Filesystem in Userspace for Linux and other UNIX-like computers. winfsp.dev...

vigolium v0.3.6

Vigolium - High-fidelity vulnerability scanner fusing agentic AI with native speed, modularity, and precision Vigolium provides two complementary scanning modes: Native Scan vigolium scan: Fast, powerful, and flexible. Deterministic, multi-phase scanning with 317 modules across content discovery,...