Red-Teaming Auto Mode: Improving Blocking Classifiers against Malign Coding Agents

To keep coding agents from going off the rails, production systems now review each proposed action with a blocking monitor that can reject it before it runs Auto Mode in Claude Code, Guardian in OpenAI's Codex. Prior evaluations of such monitors largely measure robustness to accidental harm or...

CVE-2026-57124

PraisonAI is a multi-agent teams system. Prior to 4.6.59, the default UI host applications expose POST /api/mcp/connect without mandatory authentication and accept caller-controlled command and args values that PraisonAIUI passes to StdioMCPClient to start a local process. Because the UI commands...

CVE-2026-57132

PraisonAI is an AI multi-agent framework. Prior to 4.6.62 , setting the PRAISONAI_CALL_AUTH=disabled environment variable causes the verify_token function (in agent_invoke.py) to return immediately, unconditionally bypassing all authentication on the /api/v1/agents/{id}/invoke endpoint. Because t...

CVE-2026-57122 PraisonAI: Webhook signature verification skipped (fail-open) when secret unset, allowing forged inbound webhooks (WhatsApp & Linear bots)

PraisonAI is a multi-agent teams system. Prior to 4.6.59, the WhatsApp and Linear bot webhook handlers verify HMAC signatures only when WHATSAPPAPPSECRET or LINEARWEBHOOKSECRET is configured and otherwise parse and dispatch unsigned request bodies. A remote unauthenticated client that reaches the...

OPENSUSE-SU-2026:21849-1 Security update for kimi-code

This update for kimi-code fixes the following issues: Changes in kimi-code: Update to version 0.42.0: Add an experimental Updates panel with paginated progress messages from the main agent and subagents, enabled with KIMICODEEXPERIMENTALNOTIFYUSER=1 Turn the subagent model pool, Remote Control an...

Mapping U.S. Federal AI Governance against Sector Vulnerability

Artificial intelligence AI poses different levels of risk across sectors, but are these differences reflected in U.S. federal AI governance? To help answer this question, we assess 684 federal AI governance documents for their coverage of 14 sectors and 24 AI risks. We measure coverage as breadth...

CyberStar

--- Table of Contents - Overview - Architectu...

Claude Used to Automate Exploitation and Data Theft Across Multiple Victims

Anthropic has warned that cybercriminals and state-sponsored hackers alike are using its Claude models for cyber attacks, weapons design, propaganda, and mass surveillance between December 2025 and August 2026. The threat actors, which the artificial intelligence AI company has branded Generative...

Autonomous AI Agents Compromise Thousands of Credentials in Under Six Hours

Threat actors are continuing to leverage artificial intelligence AI to streamline their operations, with one financially motivated hacking group employing an autonomous, multi-agent attack framework to carry out a large-scale credential harvesting campaign within six hours. Google Threat...

Skynet: Workflow-Level Anomaly Detection for Agentic AI Via Semantic and Structural Modeling

Agentic AI systems execute complex tasks through long-horizon workflows of planning, tool use, and multi-agent coordination. Task failures in these systems often originate from a single step, such as an injected prompt or a flawed plan, and are then amplified through downstream dependencies as th...

Cost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attribution

Ransomware detection and family attribution require analysis of different modalities because it can use packing, obfuscation, process manipulation and runtime evasion techniques. However, conventional multimodal usually uses all available modalities for every sample resulting in unnecessary...

my-dshrness-aipentest

DSH PenTest Workflow v4.2 A multi-agent penetration testing w...

Awesome-LLMs-for-Vulnerability-Detection — Updated!

Awesome Large Language Models for Vulnerability Detection A curated list of papers, projects, and agent skills on using LLMs for vulnerability detection and discovery. 📄 Papers Only showing 2025 and later. For earlier work, see Papers Archive 2024 and earlier. Title| Venue| Year| Paper| Github...

redteam-skill

Redteam Skill — Multi-Agent Autonomous Penetration Testing Pi...

SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems

Safe agents can fail together. Multi-agent LLM systems MAS move information, state, decisions, and authority across principal boundaries, creating failures that local checks may miss. Without an execution-level view, a multi-agent setting can easily be mistaken for evidence of a genuinely...

From Concept to Context Engine: How Wiz Built AI-Powered Data Discovery

Inside the multi-agent pipeline and feedback loops that turned a bucket scanner into a context engine...

zen-ai

Zen Open-source offensive security agents. Autonomous pen...

CVE-2026-55541

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, praisonai serve agents and praisonai serve unified parse --api-key but createagentsapp and createunifiedapp do not install a credential check. Unauthenticated callers can reach POST /agents and POST /api/v1/agents/id/invoke. This...

CVE-2026-55539 PraisonAI: [Auth Bypass] PraisonAI async Jobs API (`/api/v1/runs`) has no authentication — unauthenticated job execution, result theft, cancel and delete

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, the Jobs API createapp function mounts /api/v1/runs without authentication. Any reachable caller can submit jobs, read results, cancel runs, or delete jobs using operator credentials. The fix adds PRAISONAIJOBSAPIKEY middleware f...

CVE-2026-55539

PraisonAI, a multi-agent teams system, exposed its async Jobs API (/api/v1/runs) without authentication prior to version 4.6.51. The create_app function mounted the endpoint with no access control, allowing any reachable caller to submit jobs, read results, cancel runs, or delete jobs using opera...