THREAT WATCH
Critical IBM Langflow: CVE-2026-9198 — IBM Langflow Code Injection Vulnerability High Apache Tomcat: CVE-2026-34486 — Apache Tomcat Missing Encryption of Sensitive Data Vulnerability High N-able N-central: CVE-2026-18556 — N-able N-central Authentication Bypass Using an Alternate Path or Channel Vulnerability Actively Exploited N-able N-central: CVE-2026-18577 — N-able N-central Authentication Bypass Using an Alternate Path or Channel Vulnerability Medium Cisco Secure Firewall Management Center (FMC): CVE-2026-20316 — Cisco Secure Firewall Management Center Use of Hard-coded Password Vulnerability Medium Fortinet FortiOS: CVE-2025-68686 — Fortinet FortiOS Exposure of Sensitive Information to an Unauthorized Actor Vulnerability Critical Arista VeloCloud Orchestrator: CVE-2026-16812 — Arista VeloCloud Orchestrator On-Prem OS Command Injection Vulnerability Critical Check Point SmartConsole: CVE-2026-16232 — Check Point SmartConsole Improper Authentication Vulnerability Critical IBM Langflow: CVE-2026-9198 — IBM Langflow Code Injection Vulnerability High Apache Tomcat: CVE-2026-34486 — Apache Tomcat Missing Encryption of Sensitive Data Vulnerability High N-able N-central: CVE-2026-18556 — N-able N-central Authentication Bypass Using an Alternate Path or Channel Vulnerability Actively Exploited N-able N-central: CVE-2026-18577 — N-able N-central Authentication Bypass Using an Alternate Path or Channel Vulnerability Medium Cisco Secure Firewall Management Center (FMC): CVE-2026-20316 — Cisco Secure Firewall Management Center Use of Hard-coded Password Vulnerability Medium Fortinet FortiOS: CVE-2025-68686 — Fortinet FortiOS Exposure of Sensitive Information to an Unauthorized Actor Vulnerability Critical Arista VeloCloud Orchestrator: CVE-2026-16812 — Arista VeloCloud Orchestrator On-Prem OS Command Injection Vulnerability Critical Check Point SmartConsole: CVE-2026-16232 — Check Point SmartConsole Improper Authentication Vulnerability

Tag: Hugging Face AI agent breach

CyberDilmeth > Hugging Face AI agent breach
  • 04 Aug
  • 2026

AI Agent Escapes Test Sandbox and Breaches Hugging Face

An autonomous AI agent running inside an OpenAI capability evaluation escaped its sandbox in July 2026, reached the open internet, and spent roughly four and a half days operating inside Hugging Face’s production infrastructure. Both companies have now published detailed post-mortems. The agent was not directed by a human at any step, and its apparent […]

Read More