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
4,331

AI/ML CVEs Tracked

535

Critical

108

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 1295 results — High severity, no patch
HIGHEXPLOIT AVAIL

stable-diffusion.cpp: heap overflow via crafted .ckpt model

CVE-2026-47750
7.8
EPSS 0.2%
Supply ChainCode ExecutionModelInference
5 ATLAS
HIGH

OpenClaw: PowerShell allowlist bypass enables arbitrary RCE

CVE-2026-53836
8.8
EPSS 0.5%
Auth BypassCode ExecutionAgent
OpenClawCWE-18434 ATLAS1 incident
HIGH

OpenClaw: auth bypass in QQBot pre-dispatch commands

CVE-2026-53834
7.5
EPSS 0.2%
Auth BypassCode ExecutionAgentPlugin
OpenClawCWE-86333 ATLAS1 incident
HIGH

OpenClaw: auth bypass allows agent config mutation

CVE-2026-53833
7.7
EPSS 0.2%
Auth BypassData LeakageAgentFramework
openclawCWE-29033 ATLAS
HIGH

OpenClaw: identity header spoof grants operator access

CVE-2026-53832
7.7
EPSS 0.1%
Auth BypassCode ExecutionAgentFramework
OpenClawCWE-29035 ATLAS1 incident
HIGH

OpenClaw: safe-bin allowlist bypass via shell expansion

CVE-2026-53831
8.3
EPSS 0.2%
Code ExecutionData ExtractionAuth BypassAgentPlugin
OpenClawCWE-36735 ATLAS1 incident
HIGH

OpenClaw: approval truncation bypasses exec oversight

CVE-2026-53829
8.0
EPSS 0.2%
Auth BypassCode ExecutionAgentPlugin
OpenClawCWE-45134 ATLAS2 incidents
HIGH

OpenClaw: auth bypass enables owner command execution

CVE-2026-53828
8.8
EPSS 0.3%
Auth BypassCode ExecutionAgentFramework
OpenClawCWE-86335 ATLAS1 incident
HIGH

OpenClaw: privilege escalation via Slack display name spoofing

CVE-2026-53823
8.1
EPSS 0.2%
Auth BypassSocial EngineeringAgent
OpenClawCWE-29034 ATLAS1 incident
HIGH

OpenClaw: TOCTOU command injection bypasses allowlist

CVE-2026-53822
8.8
EPSS 1.1%
Code ExecutionAuth BypassAgentPlugin
OpenClawCWE-36734 ATLAS1 incident
HIGH

OpenClaw: auth bypass grants admin RPC via WebSocket

CVE-2026-53821
8.8
EPSS 0.3%
Auth BypassCode ExecutionAgentFramework
OpenClawCWE-86234 ATLAS1 incident
HIGHEXPLOIT AVAIL

ChromaDB: RCE via trust_remote_code in collection update

CVE-2026-45833
8.8
EPSS 0.3%
Code ExecutionSupply ChainRAGFramework
chromadbCWE-941.9K6 ATLAS
HIGH

ChromaDB: V1 auth bypass exposes all tenant collections

CVE-2026-45832
8.8
EPSS 0.3%
Auth BypassData ExtractionRAGFramework
chromadb1.9K4 ATLAS
HIGH

ChromaDB: RBAC bypass enables cross-tenant data access

CVE-2026-45831
8.8
EPSS 0.2%
Auth BypassData ExtractionData LeakageRAGFramework
chromadbCWE-8631.9K5 ATLAS
HIGH

ChromaDB: auth bypass exposes any tenant's collections

CVE-2026-45830
8.8
EPSS 0.3%
Auth BypassData ExtractionData LeakageRAG
chromadbCWE-2661.9K5 ATLAS
HIGH

OpenClaw: auth bypass allows unauthorized command execution

CVE-2026-53807
8.8
EPSS 0.3%
Auth BypassCode ExecutionAgentFramework
OpenClawCWE-86334 ATLAS1 incident
HIGH

Langflow: IDOR bypasses auth, exposes sensitive AI configs

CVE-2026-7787
8.1
EPSS 0.2%
Auth BypassData ExtractionFrameworkAgent
langflowCWE-6394 ATLAS
HIGH

Xibo CMS: Stored XSS + iframe sandbox escape via DataSet

CVE-2026-42558
7.6
EPSS 0.1%
Code ExecutionAuth BypassData ExtractionFramework
CWE-795 ATLAS
HIGH

Linux Xe iGPU: cache-bypass leaks cross-process stale data

CVE-2026-46309
7.0
EPSS 0.1%
Data LeakagePrivacy ViolationInferenceModel
3 ATLAS
HIGHEXPLOIT AVAIL

Flowise: mass-assignment allows cross-workspace takeover

CVE-2026-46480
8.8
EPSS 0.3%
Auth BypassData ExtractionAgentFramework
flowise4 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