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
HIGH

PraisonAI: sandbox escape via silent Landlock fallback

GHSA-6jcq-6546-qrrw
8.8
Code ExecutionData ExtractionAuth BypassAgentFramework
praisonaiagentsCWE-668205 ATLAS
HIGH

PraisonAI: workflow policy bypass enables shell RCE

GHSA-7qw2-w5rc-37x2
7.8
Auth BypassCode ExecutionAgentFramework
praisonaiagentsCWE-78205 ATLAS
HIGHEXPLOIT AVAIL

picklescan: arbitrary file read bypasses RCE blocklist

CVE-2026-53872
7.5
EPSS 0.5%
Data ExtractionSupply ChainFrameworkModel
picklescan35 ATLAS
HIGHEXPLOIT AVAIL

PickleScan: pty.spawn bypass enables RCE in model scans

CVE-2025-71322
8.8
EPSS 0.4%
Supply ChainCode ExecutionModelFramework
PickleScanCWE-69335 ATLAS
HIGH

WPBot Pro: subscriber file deletion → system DoS

CVE-2025-60223
7.7
EPSS 0.4%
DoSAuth BypassPlugin
wpbot-pro3 ATLAS
HIGH

OpenClaw: allowlist bypass allows unauthorized shell exec

CVE-2026-53866
8.1
EPSS 0.3%
Auth BypassCode ExecutionAgentFramework
openclawCWE-18435 ATLAS
HIGH

OpenClaw: path traversal enables arbitrary local code exec

CVE-2026-53865
7.1
EPSS 0.1%
Code ExecutionSupply ChainAgentFramework
openclawCWE-42633 ATLAS
HIGH

OpenClaw: env var bypass enables child process code exec

CVE-2026-53864
8.1
EPSS 0.2%
Code ExecutionData ExtractionAuth BypassAgentFrameworkPlugin
openclawCWE-18434 ATLAS
HIGH

OpenClaw: access control bypass via unvalidated group ID

CVE-2026-53863
7.1
EPSS 0.2%
Auth BypassCode ExecutionAgentPlugin
openclawCWE-63933 ATLAS
HIGH

OpenClaw: env var injection loads malicious runtime deps

CVE-2026-53858
7.1
EPSS 0.1%
Supply ChainCode ExecutionAgentFramework
openclawCWE-42633 ATLAS
HIGH

OpenClaw: display name spoofing bypasses agent allowFrom policy

CVE-2026-53857
8.1
EPSS 0.2%
Auth BypassSocial EngineeringData LeakageAgentFramework
openclawCWE-29035 ATLAS
HIGH

OpenClaw: allowlist bypass enables shell code execution

CVE-2026-53855
8.1
EPSS 0.3%
Auth BypassCode ExecutionAgentPlugin
openclawCWE-18435 ATLAS
HIGH

OpenClaw: exec allowlist bypass enables unrestricted RCE

CVE-2026-53853
8.3
EPSS 0.3%
Auth BypassCode ExecutionAgentFramework
openclawCWE-69334 ATLAS
HIGH

OpenClaw: auth bypass via Discord display name spoofing

CVE-2026-53849
8.1
EPSS 0.3%
Auth BypassSocial EngineeringAgent
openclawCWE-29034 ATLAS
HIGH

OpenClaw: path traversal enables arbitrary package-manager exec

CVE-2026-53846
7.1
EPSS 0.1%
Supply ChainCode ExecutionAgentFramework
openclawCWE-42634 ATLAS
HIGH

OpenClaw: revocation bypass grants node token access

CVE-2026-53843
8.8
EPSS 0.3%
Auth BypassAgent
openclawCWE-28434 ATLAS
HIGH

OpenClaw: env var injection enables arbitrary code exec

CVE-2026-53842
7.1
EPSS 0.1%
Code ExecutionSupply ChainAgent
openclawCWE-42635 ATLAS
HIGH

OpenClaw: credential exfiltration via MCP header forwarding

CVE-2026-53840
7.1
EPSS 0.2%
Data LeakageData ExtractionAuth BypassAgentAPIPlugin
openclawCWE-20035 ATLAS
HIGHEXPLOIT AVAIL

stable-diffusion.cpp: heap overflow in .ckpt model parser

CVE-2026-47749
7.8
EPSS 0.2%
Supply ChainCode ExecutionModelInference
CWE-1224 ATLAS
HIGHEXPLOIT AVAIL

stable-diffusion.cpp: .ckpt heap overflow enables RCE

CVE-2026-47747
7.8
EPSS 0.2%
Supply ChainCode ExecutionModelInference
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