AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
3,019

AI/ML CVEs Tracked

424

Critical

113

New This Week

19

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 297 results — Critical severity, no patch
CRITICAL EXPLOIT AVAIL

GPT-SoVITS: unauthenticated RCE via webui.py

CVE-2026-63766
9.8
EPSS 1.7%
Code Execution Inference Framework
CWE-78 2 ATLAS
CRITICAL

ktransformers: unauth pickle RCE via ZMQ socket

CVE-2026-63767
9.8
EPSS 0.7%
Code Execution Auth Bypass Inference Framework
ktransformers 9.0K 3 ATLAS
CRITICAL

Langflow: hard-coded credentials enable takeover

CVE-2026-13446
9.8
EPSS 0.2%
Auth Bypass Code Execution Framework Agent
langflow CWE-798 3 ATLAS
CRITICAL

Langflow: path traversal writes arbitrary files

CVE-2026-8859
9.9
EPSS 0.4%
Code Execution Framework Agent Plugin
langflow CWE-22 2 ATLAS
CRITICAL

Langflow: DB manipulation escalates to superuser RCE

CVE-2026-8635
9.9
EPSS 0.3%
Auth Bypass Code Execution Framework Agent
langflow CWE-94 4 ATLAS
CRITICAL

Langflow: webhook auth bypass enables unauth RCE

CVE-2026-8505
9.8
EPSS 0.6%
Auth Bypass Code Execution Framework Agent
langflow 3 ATLAS
CRITICAL

Langflow: unsandboxed exec() enables full RCE

CVE-2026-8481
9.9
EPSS 0.5%
Code Execution Framework Agent
langflow CWE-94 3 ATLAS
CRITICAL

Langflow: pickle deserialization RCE via disk cache (CVSS 9.9)

CVE-2026-8476
9.9
EPSS 0.5%
Code Execution Supply Chain Framework Agent Plugin
langflow CWE-502 4 ATLAS
CRITICAL

Langflow: unauthenticated RCE via public flow endpoint

CVE-2026-13448
9.8
EPSS 0.5%
Code Execution Auth Bypass Agent Framework Plugin
langflow 3 ATLAS
CRITICAL

Langflow: code injection bypasses ToolGuard, enables RCE

CVE-2026-9135
9.9
EPSS 0.4%
Code Execution Auth Bypass Framework Agent Plugin
langflow CWE-94 4 ATLAS
CRITICAL

Langflow: unauth request grants superuser token

CVE-2026-9103
9.8
EPSS 0.4%
Auth Bypass Code Execution Data Leakage Framework Agent
langflow CWE-306 4 ATLAS
CRITICAL SCANNER

Langflow: token forgery + exec() chain to RCE

CVE-2026-9198
9.8
EPSS 17.1%
Auth Bypass Code Execution Framework Agent
Langflow OSS CWE-94 4 ATLAS
CRITICAL

Langflow: unauth signup chains to RCE

CVE-2026-9202
9.8
EPSS 0.3%
Auth Bypass Code Execution Framework Agent
Langflow OSS CWE-306 4 ATLAS
CRITICAL EXPLOIT AVAIL

AVideo: stored XSS in YPTSocket enables admin takeover

CVE-2026-54458
9.6
EPSS 0.3%
Code Execution Auth Bypass Data Leakage Plugin
CWE-79 1 ATLAS
CRITICAL SCANNER

LiteLLM: RCE via unsanitized MCP server config

CVE-2026-30623
9.8
EPSS 6.0%
Code Execution Plugin Agent Inference
litellm 6 4 ATLAS
CRITICAL

Flowise: hardcoded JWT secrets enable full auth bypass

CVE-2026-56271
9.8
EPSS 0.4%
Auth Bypass Privacy Violation Code Execution Agent Framework API
Flowise CWE-321 3 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: RCE via unsandboxed LLM code execution

CVE-2026-61447
10.0
EPSS 0.7%
Prompt Injection Code Execution Agent
praisonai CWE-94 1 5 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: AICoder root RCE via unsanitized tool calls

CVE-2026-61445
9.9
EPSS 0.5%
Code Execution Prompt Injection Agent Plugin
praisonai CWE-22 1 5 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: SQL/CQL injection via unvalidated vector dim

CVE-2026-60090
9.8
EPSS 0.4%
Code Execution Data Leakage DoS RAG Agent Framework
praisonai CWE-89 1 3 ATLAS
CRITICAL EXPLOIT AVAIL

mcp-server-kubernetes: arg injection exfils bearer token

CVE-2026-61459
9.8
EPSS 0.5%
Auth Bypass Data Leakage Agent Plugin
mcp-server-kubernetes 1 4 ATLAS

Frequently asked questions

What is an AI security threat feed?

An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.

Which sources are the AI CVEs tracked from?

CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.

What AI systems do these vulnerabilities affect?

Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.

How often is the AI threat feed updated?

The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.

Is the AI security feed free?

Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.

Need deeper analysis?

Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.

Start 14-Day Free Trial