Posts

FastGPT NoSQL Injection Auth Bypass (CVE-2026-40351/40352)

FastGPT, an open-source AI agent building platform, ships with critical NoSQL injection flaws that allow unauthenticated admin login and authenticated account takeover.

GreyNoise — 91,403 Attack Sessions Target Exposed LLM Infrastructure

GreyNoise honeypots captured 91,403 attack sessions against exposed LLM endpoints between October 2025 and January 2026, revealing systematic reconnaissance and exploitation of misconfigured AI deployments.

Hadrian — 70 AI Offensive Security Tools Cataloged as Pen Testing Economics Collapse

Hadrian catalogs 70 open-source AI pentesting tools as of March 2026, with agents achieving IP-to-shell for under $1 and 156x cost reduction versus human-led engagements.

XCIT Threat Labs — Malicious LLM Routers Inject Payloads and Steal Credentials

Audit of 428 LLM API routers finds active payload injection in 9 services, credential harvesting in 17, and confirmed crypto wallet draining — exposing a hidden supply-chain risk for AI agent deployments.

mcp-neo4j-cypher Read-Only Mode Bypass via Stored Procedures (CVE-2026-35402)

CVE-2026-35402 in mcp-neo4j-cypher lets LLM agents bypass read-only restrictions using CALL stored procedures, enabling data modification and SSRF.

Enterprises Stuck at Monitoring While AI Agents Need Isolation

VentureBeat survey finds most enterprises observe but cannot enforce or isolate AI agent behavior, while 97% of security leaders expect a major agent-driven incident within a year.

Cisco AI Defense — Open-Source Agent Security Toolkit Launch

Cisco open-sources a comprehensive AI agent security toolkit including DefenseClaw, MCP Scanner, Skill Scanner, A2A Scanner, and AI BOM — addressing the full agentic AI threat surface.

Gambit Security — Single Hacker Used Claude Code and ChatGPT to Breach Nine Mexican Government Agencies

A single threat actor leveraged Claude Code and GPT-4.1 to compromise nine Mexican government agencies, stealing 195M citizen records in a campaign that ran from December 2025 to February 2026.

Abnormal Security — ATHR: AI Voice Agents Automate Full Vishing Attack Chain

Abnormal Security discovers ATHR, a commercial cybercrime platform that uses AI voice agents to automate the entire telephone-oriented attack delivery (TOAD) chain — from email lures to credential harvesting for Google, Microsoft, and Coinbase.

Cisco Talos — n8n AI Workflow Platform Abused for Malware Delivery and Device Fingerprinting

Cisco Talos reports a 686% increase in phishing emails abusing n8n AI workflow automation webhooks to deliver malware and fingerprint devices via trusted cloud domains.

Cloudflare — Enterprise MCP Reference Architecture for Secure Agentic Workflows

Cloudflare publishes its internal MCP security architecture covering authorization controls, prompt injection defense, supply chain governance, and Shadow MCP detection for enterprise AI agent deployments.

Google Cloud Threat Intelligence — Defending Enterprises Against AI-Powered Exploitation

Google Cloud/Mandiant warn that AI models are compressing the zero-day attack timeline, enabling mass exploitation campaigns, and call for AI-integrated defensive roadmaps to counter machine-speed threats.

Apple Intelligence — Prompt injection bypasses on-device AI guardrails (RSAC 2026)

RSAC 2026 researchers achieved 76% prompt injection success rate against Apple Intelligence using Neural Exec and Unicode bidirectional tricks, patched in iOS 26.4 / macOS 26.4.

Flowise — CVSS 10.0 CustomMCP RCE enables full server compromise (CVE-2025-59528)

Microsoft — AI-enabled device code phishing campaign bypasses MFA at scale (April 2026)

Microsoft documents an AI-driven phishing campaign using dynamic code generation, generative AI lures, and serverless infrastructure to bypass MFA and compromise organizational accounts.

Capsule Security — ShareLeak and PipeLeak prompt injection in Copilot Studio and Agentforce

Capsule Security disclosed CVE-2026-21520 (ShareLeak) in Microsoft Copilot Studio and PipeLeak in Salesforce Agentforce — indirect prompt injection via public forms leading to data exfiltration.

OpenClaw — CVE-2026-33579 Privilege Escalation via Missing Scope Validation in Device Pairing

ChatboxAI — MCP StdioClientTransport OS Command Injection (CVE-2026-6130)

OpenAI — Axios Supply Chain Compromise Impacts macOS App Certification

OpenAI discloses Axios npm supply chain attack affecting GitHub Actions workflow with access to macOS app signing certificates, highlighting critical AI infrastructure supply chain risks.

arXiv — MCP-DPT: Defense Placement Taxonomy for Model Context Protocol Security

New arXiv research introduces MCP-DPT, a defense-placement taxonomy that maps 49 MCP-specific attacks to architectural layers and identifies critical security gaps in AI agent ecosystems.