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
4,307

AI/ML CVEs Tracked

533

Critical

95

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 1908 results — High severity
HIGH

OpenClaw: RCE via malicious repo setup-api.js

GHSA-r39h-4c2p-3jxp
7.8
Supply ChainCode ExecutionAgentPlugin
openclawPatch: 2026.4.23CWE-9434 ATLAS1 incident
HIGH

Jupyter Server: CORS bypass via regex anchor omission

CVE-2026-40110
7.1
EPSS 0.3%
Auth BypassCode ExecutionData ExtractionFrameworkAPI
jupyter-serverPatch: 2.18.0CWE-7771.9K4 ATLAS
HIGHEXPLOIT AVAIL

Jupyter Server: path traversal leaks sibling directories

CVE-2026-35397
7.1
EPSS 0.6%
Data ExtractionPrivacy ViolationFramework
jupyter-serverPatch: 2.18.0CWE-221.9K4 ATLAS
HIGH

openclaw: TOCTOU sandbox escape via symlink swap

GHSA-wppj-c6mr-83jj
--
Code ExecutionSupply ChainAuth BypassAgentPlugin
openclawPatch: 2026.4.22CWE-36734 ATLAS1 incident
HIGH

openclaw: MCP owner-context spoofing, privilege escalation

GHSA-r6xh-pqhr-v4xh
--
Auth BypassCode ExecutionAgentFramework
openclawPatch: 2026.4.22CWE-28434 ATLAS1 incident
HIGH

GnuTLS: DTLS fragment heap overflow, DoS on AI inference

CVE-2026-33846
7.5
EPSS 1.3%
DoSCode ExecutionInference
rhaiis/vllm-rocm-rhel9942 ATLAS
HIGH

Langflow: RCE exposes API keys and DB credentials

CVE-2026-6543
8.8
EPSS 0.5%
Code ExecutionData ExtractionSupply ChainFrameworkAgent
langflowCWE-945 ATLAS
HIGH

Langflow: IDOR exposes cross-tenant flow data and deletion

CVE-2026-6542
8.1
EPSS 0.2%
Data ExtractionPrivacy ViolationAuth BypassFrameworkAgent
langflowCWE-6395 ATLAS
HIGH

Langflow Desktop: IDOR leaks user images unauthenticated

CVE-2026-4503
7.5
EPSS 0.3%
Privacy ViolationData ExtractionAuth BypassFrameworkAgent
langflowCWE-6393 ATLAS
HIGH

n8n-mcp: SSRF bypass via IPv6 leaks API keys

CVE-2026-42449
8.5
EPSS 0.2%
Data ExtractionAuth BypassSupply ChainAgentPlugin
n8n-mcpPatch: 2.47.14CWE-918165 ATLAS
HIGH

GnuTLS: DTLS integer underflow enables OOB read/DoS

CVE-2026-33845
7.5
EPSS 2.1%
DoSData LeakageInferenceAPI
rhaiis/vllm-rocm-rhel9942 ATLAS
HIGH

Jupyter Notebook: stored XSS enables full account takeover

CVE-2026-40171
--
EPSS 0.5%
Auth BypassCode ExecutionData ExtractionFrameworkTraining Data
@jupyterlab/help-extensionPatch: 4.5.7CWE-791.9K7 ATLAS
HIGHEXPLOIT AVAIL

marked: infinite recursion DoS crashes Node.js via OOM

CVE-2026-41680
7.5
EPSS 0.3%
DoSFramework
markedPatch: 18.0.2CWE-40016.9K4 ATLAS
HIGH

litellm: RCE via MCP test endpoints privilege bypass

GHSA-v4p8-mg3p-g94g
--
Auth BypassCode ExecutionAPIInference
litellmPatch: 1.83.7CWE-7865 ATLAS
HIGH

Claude Code: git worktree trust bypass executes hooks

CVE-2026-40068
--
EPSS 0.3%
Auth BypassCode ExecutionSupply ChainAgentFrameworkPlugin
@anthropic-ai/claude-codePatch: 2.1.84CWE-205 ATLAS
HIGH

Ray: Parquet RCE via Arrow extension deserialization

CVE-2026-41486
--
EPSS 0.5%
Code ExecutionSupply ChainFrameworkTraining Data
rayPatch: 2.55.0CWE-946425 ATLAS
HIGH

LiteLLM: RCE via unsandboxed prompt template rendering

GHSA-xqmj-j6mv-4862
--
Code ExecutionData ExtractionInferenceAPI
litellmPatch: 1.83.7CWE-133665 ATLAS
HIGHEXPLOIT AVAIL

Flowise: unauth API key abuse via TTS endpoint IDOR

CVE-2026-41279
7.5
EPSS 0.3%
Auth BypassDoSData ExtractionAgentAPIFramework
flowiseCWE-6395 ATLAS
HIGHEXPLOIT AVAIL

Flowise: credential exposure in public chatflow API

CVE-2026-41278
7.5
EPSS 0.4%
Data ExtractionAuth BypassAgentFramework
flowiseCWE-2005 ATLAS
HIGHEXPLOIT AVAIL

Flowise: mass assignment enables cross-workspace IDOR

CVE-2026-41277
8.8
EPSS 3.1%
Auth BypassData ExtractionModel PoisoningAgentRAGFramework
flowiseCWE-2844 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