171 matches found
socbench
socbench Benchmark frontier reasoning LLMs as SOC agents on raw NetFlow data. socbench benchmarks frontier reasoning models as SOC agents: each model runs a bounded multi-turn agent loop against a deterministic, pre-indexed NetFlow corpus, with persona-scoped read-only tools, fixed dollar caps pe...
Malware in persona-ai-sdk
Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be rotated immediately from a different computer. The package should be removed, but as full control of the computer may have been given to an outsid...
MAL-2026-18463 Malicious code in persona-ai-sdk (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 51f4740acba00f4f8441d73ea1fd5399562db72b59c9f618a15f97866502ab17 The package's declared main index.mjs re-exports personas.mjs, which at module top level imports cssVarMap from./cache-warm.mjs and invokes it in an...
Malicious code in persona-ai-sdk (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 51f4740acba00f4f8441d73ea1fd5399562db72b59c9f618a15f97866502ab17 The package's declared main index.mjs re-exports personas.mjs, which at module top level imports cssVarMap from./cache-warm.mjs and invokes it in an...
Persona Guardrail: A Production-Grade Defense Framework for Agentic Systems
Large language model-based agents are increasingly deployed to perform domain-specific tasks by interacting with enterprise knowledge, tools, and external services. Existing runtime guardrails primarily target prompt injection and other attack-specific behaviors under a black-box threat model, bu...
The story behind the intelligence
Welcome to this week's edition of the Threat Source newsletter. Our goal is to get accurate threat intelligence to our audience as quickly as possible, with all the context you need to ask the right questions of your own environment: How at risk are we from this threat? Are we prepared for it? An...
CVE-2026-71424
Onyx is an open-source AI platform. Prior to 3.1.10, 3.2.14, and 4.0.0, Onyx's GET /api/mcp/servers and GET /api/mcp/servers/persona/personaid endpoints expose another user's OAuth Authorization header because OnyxTokenStorage.settokens and OnyxTokenStorage.setclientinfo in...
CVE-2026-71424: Exposure of Sensitive Information to an Unauthorized Actor
Onyx is an open-source AI platform. Prior to 3.1.10, 3.2.14, and 4.0.0, Onyx's GET /api/mcp/servers and GET /api/mcp/servers/persona/personaid endpoints expose another user's OAuth Authorization header because OnyxTokenStorage.settokens and OnyxTokenStorage.setclientinfo in...
bxploit
BXPLOIT AI-Powered Penetration Testing Framework built on Kim...
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...
Persona Password Profiler
Collect OSINT on a person name/email or company domain, then propose 20 contextually relevant password candidates for authorized assessments. from kittysploit import import json import os import re from urllib.parse import urlparse from core.osint.passwordprofiling import applyrdapcompanyname,...
Malicious code in 0x2ai-demo3 (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector a36d5f023e4740169d1e1e7a56ebe32552cfdc4a05bf50ecc0b648ecea502c0d On npm install, scripts/postinstall.cjs copies the entire payload/ tree into process.env.INITCWD the directory the developer ran the install from usi...
MAL-2026-5590 Malicious code in 0x2ai-demo3 (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector a36d5f023e4740169d1e1e7a56ebe32552cfdc4a05bf50ecc0b648ecea502c0d On npm install, scripts/postinstall.cjs copies the entire payload/ tree into process.env.INITCWD the directory the developer ran the install from usi...
MAI-2025-0008
Multimodal Large Language Models MLLMs are susceptible to a sophisticated attack vector that exploits narrative-driven visual storytelling and role immersion to bypass inherent safety protocols. This attack, known as MIRAGE, strategically decomposes malicious queries into triplets consisting of...
CVE-2026-32114: Authorization Bypass Through User-Controlled Key
Discourse is an open-source discussion platform. Prior to versions 2026.3.0-latest.1, 2026.2.1, and 2026.1.2, there is an Insecure Direct Object Reference IDOR vulnerability that allows any authenticated user to access metadata about AI personas, features, and LLM models by providing their...
Malicious code in wn-idv-persona-client (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 77973c6ca0ba60bf7105d4250b88b0fd7b3304dd3fe9ead1072912d8e724b21f The package wn-idv-persona-client was found to contain malicious code. Source: ossf-package-analysis...
MAL-2026-1584 Malicious code in wn-idv-persona-client (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 77973c6ca0ba60bf7105d4250b88b0fd7b3304dd3fe9ead1072912d8e724b21f The package wn-idv-persona-client was found to contain malicious code. Source: ossf-package-analysis...
Blueprint-POC
Sales-to-Delivery Agent Orchestration System - POC Phase 1...
Roblox gives predators “powerful tools” to target children, says LA County
Los Angeles County has sued online gaming company Roblox, adding to a series of suits that accuse the virtual worlds platform of misleading parents into thinking it's safe while leaving children exposed to predators and sexually explicit content. The February 19 filing makes LA County the first...
A week in security (February 16 – February 22)
Last week on Malwarebytes Labs: Age verification vendor Persona left frontend exposed, researchers say Facebook ads spread fake Windows 11 downloads that steal passwords and crypto wallets AI-generated passwords are a security risk Intimate products maker Tenga spilled customer data Meta patents ...