Ai-Infrastructure
LMDeploy CVE-2026-33626: SSRF in LLM Inference Server Exploited 12 Hours After Disclosure, Honeypot Sees AWS IMDS Theft
A 7.5-severity SSRF in Shanghai AI Lab's LMDeploy LLM serving toolkit was hit in the wild within 12h31m of the GitHub advisory. Sysdig's honeypot caught an attacker using the vision-language image loader to scrape AWS instance metadata, then pivot to internal Redis and MySQL.
LMDeploy SSRF (CVE-2026-33626) Weaponized in 12 Hours to Loot GPU IAM Credentials
A Server-Side Request Forgery in LMDeploy's vision-language image loader turned LLM inference nodes into SSRF primitives for cloud metadata theft — exploited 12 hours and 31 minutes after disclosure.
Self-Hosted and Unprotected: The AI Workflow Tool Security Crisis
Langflow, Flowise, n8n, ComfyUI — every major self-hosted AI workflow tool has shipped unauthenticated RCE vulnerabilities in 2026. This isn't a coincidence. It's a structural failure baked into how these tools were designed.
Over 1,000 Exposed ComfyUI Instances Hijacked for Cryptomining and Proxy Botnet
Active campaign targets unauthenticated ComfyUI deployments across cloud providers, enlisting them into Monero mining and a Hysteria V2 proxy botnet via malicious custom nodes.
Flowise AI Under Active Exploitation: CVSS 10.0 RCE via CustomMCP Node Hits 12,000+ Exposed Instances
Critical unauthenticated RCE in Flowise AI's CustomMCP node (CVE-2025-59528, CVSS 10.0) is under active exploitation. Over 12,000 instances are exposed. Patch to 3.0.6 immediately.
Langflow's 'Patched' Version Is Still Exploitable — CVE-2026-33017 Deadline Hits April 8
JFrog confirms Langflow 1.8.2 remains vulnerable to CVE-2026-33017 unauthenticated RCE despite being widely reported as fixed. CISA KEV deadline is April 8.