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
3,590

AI/ML CVEs Tracked

481

Critical

95

New This Week

24

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 280 results — Critical severity, Active exploitation
CRITICAL EXPLOIT AVAIL

LMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy

CVE-2025-59953
9.8
EPSS 0.7%
lmdeploy Patch: 0.10.2 CWE-502 1
CRITICAL EXPLOIT AVAIL

PraisonAI is a multi-agent teams system. Prior to 0.1.6, praisonai_platform/services/auth_service.py falls back to the public dev-secret-change-me HS256...

CVE-2026-57148
9.8
EPSS 0.4%
CWE-287
CRITICAL EXPLOIT AVAIL

PraisonAI is a multi-agent teams system. From 1.5.0 until 1.7.2, MCPServer.startHttp() in src/praisonai-ts/src/mcp/server.ts binds without a host restriction...

CVE-2026-57139
9.8
EPSS 0.4%
CWE-306
CRITICAL EXPLOIT AVAIL

PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, codeMode in src/praisonai-ts/src/tools/builtins/code-mode.ts executes untrusted JavaScript...

CVE-2026-57138
9.9
EPSS 0.4%
CWE-184
CRITICAL EXPLOIT AVAIL

PraisonAI: no-auth API exposes agent execution

CVE-2026-57131
9.8
EPSS 1.0%
Auth Bypass Code Execution Data Leakage Framework Agent API
praisonai 1 6 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: auth middleware fails open, exposes agents

CVE-2026-57127
9.8
EPSS 0.9%
Auth Bypass Code Execution Data Leakage Agent API Plugin
praisonai 1 3 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: unauth RCE via MCP connect endpoint

CVE-2026-57124
9.8
EPSS 0.6%
Auth Bypass Code Execution Agent Plugin
praisonai CWE-78 1 4 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: unauth RCE via YAML approval bypass

CVE-2026-57125
9.8
EPSS 0.4%
Auth Bypass Code Execution Agent Framework
praisonai CWE-306 1 4 ATLAS
CRITICAL EXPLOIT AVAIL

Mistral Vibe: env-var trick bypasses command allowlist

CVE-2026-87987
--
EPSS 0.3%
Code Execution Auth Bypass Agent Framework
mistral-vibe 492 5 ATLAS
CRITICAL EXPLOIT AVAIL

NLTK: pickle allowlist bypass enables RCE

CVE-2026-79657
--
EPSS 1.2%
Code Execution Supply Chain Framework Model
nltk Patch: 3.10.3 CWE-502 25.2K 4 ATLAS
CRITICAL EXPLOIT AVAIL

unstructured: SSRF via url= param exposes internal APIs

CVE-2026-71428
9.3
EPSS 0.3%
Data Leakage Auth Bypass DoS Framework RAG Agent
unstructured Patch: 0.24.0 CWE-601 3 ATLAS
CRITICAL EXPLOIT AVAIL

Langflow: auth'd RCE bypasses custom-component block

CVE-2026-19295
9.9
EPSS 1.8%
Code Execution Auth Bypass Framework Agent
langflow CWE-95 3 ATLAS
CRITICAL EXPLOIT AVAIL

Pimcore: DataObject field-name injection → RCE

CVE-2026-55634
9.9
EPSS 0.4%
Code Execution Auth Bypass Framework
pimcore/pimcore Patch: 12.3.10 CWE-89 505 3 ATLAS
CRITICAL EXPLOIT AVAIL

crewai-tools: Path traversal in FileWriterTool enables RCE

CVE-2026-37007
9.8
EPSS 0.7%
Code Execution Supply Chain Agent Plugin Framework
4 ATLAS
CRITICAL EXPLOIT AVAIL

LiteLLM: unauth SSTI in /prompts/test enables RCE

CVE-2026-37004
9.8
EPSS 0.5%
Code Execution Data Leakage Inference API
litellm Patch: 1.83.7 CWE-1336 6 3 ATLAS
CRITICAL EXPLOIT AVAIL

Cohere North AI: file upload flaw enables RCE

CVE-2025-61165
9.8
EPSS 0.4%
Code Execution Agent RAG
3 ATLAS
CRITICAL EXPLOIT AVAIL

Cohere North AI: missing Origin check enables CSWSH

CVE-2025-61163
9.8
EPSS 0.3%
Auth Bypass Data Leakage Agent API
3 ATLAS
CRITICAL EXPLOIT AVAIL

Chainlit: unauth RCE via MCP stdio cmd injection

CVE-2026-45018
9.8
EPSS 0.7%
Code Execution Framework Plugin
chainlit Patch: 2.12.0 CWE-78 41 3 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: WebSocket auth bypass hijacks browser agent

CVE-2026-55536
9.1
EPSS 0.3%
Auth Bypass Code Execution Privacy Violation Agent Plugin
PraisonAI Patch: 4.6.58 CWE-284 1 4 ATLAS
CRITICAL EXPLOIT AVAIL

Xinference: eval() on LLM output enables RCE

CVE-2026-61539
10.0
EPSS 0.7%
Code Execution Prompt Injection Inference API Agent
xinference Patch: 2.7.0 CWE-95 1.2K 5 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