Skip to content
Threat Feed
Subscribe

Tag

Ai-Agents

3 briefs RSS
low advisory

n8n AI Agents Module Restriction Bypass via MCP Connector (CVE-2026-59207)

The n8n AI Agents module in versions prior to 2.27.4 and between 2.28.0 and 2.28.1 failed to enforce configured 'Allowed HTTP Request Domains' restrictions, allowing an authenticated member-level user with 'use-only' access to a shared credential to bypass these domain restrictions and exfiltrate sensitive secrets to an attacker-controlled server.

n8n +1 vulnerability restriction-bypass data-exfiltration ai-agents
1t 1c
high advisory

n8n AI Agents Privilege Escalation via run_node_tool

A privilege escalation vulnerability (CVE-2026-65015) exists in n8n's AI Agents feature, allowing users with the read-only Project Viewer role to execute arbitrary tool nodes and access unauthorized credential secrets, potentially leading to arbitrary command execution on the n8n host.

n8n +1 privilege-escalation vulnerability ai-agents web-application
1r 1t 1c
high advisory

Securing AI Agents with CrowdStrike Falcon AIDR and NVIDIA NeMo Guardrails

CrowdStrike Falcon AIDR now supports NVIDIA NeMo Guardrails to protect AI agents from attacks like prompt injection, data exfiltration, and unauthorized actions, enabling organizations to deploy AI applications more securely.

ai-security prompt-injection data-protection ai-agents
2r 1t