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 1527 results — Medium severity
MEDIUM

OpenClaw: bootstrap token replay enables scope escalation

CVE-2026-53862
4.2
EPSS 0.1%
Auth BypassData ExtractionAgent
openclawCWE-26633 ATLAS
MEDIUM

OpenClaw: allowlist bypass enables arbitrary shell exec

CVE-2026-53861
6.6
EPSS 0.2%
Auth BypassCode ExecutionAgent
openclawCWE-18434 ATLAS
MEDIUM

OpenClaw: sender allowlist bypass via conversation metadata

CVE-2026-53860
4.2
EPSS 0.2%
Auth BypassCode ExecutionAgent
openclawCWE-86334 ATLAS
MEDIUM

OpenClaw: SSRF blocklist bypass via trailing-dot

CVE-2026-53859
6.5
EPSS 0.2%
Auth BypassData ExtractionAgent
openclawCWE-91834 ATLAS
MEDIUM

OpenClaw: insecure permissions expose agent config

CVE-2026-53856
5.5
EPSS 0.1%
Data ExtractionData LeakageAgent
openclawCWE-27634 ATLAS
MEDIUM

OpenClaw: privilege escalation via channel auth wildcard

CVE-2026-53854
6.5
EPSS 0.2%
Auth BypassCode ExecutionAgentFramework
openclawCWE-86333 ATLAS
MEDIUM

OpenClaw: scope bypass allows unauthorized device access

CVE-2026-53852
5.4
EPSS 0.2%
Auth BypassData ExtractionAgentAPI
openclawCWE-63633 ATLAS
MEDIUM

OpenClaw: Slack reaction bypass triggers agent pipeline

CVE-2026-53851
5.3
EPSS 0.2%
Auth BypassPrompt InjectionAgentPlugin
openclawCWE-86234 ATLAS
MEDIUM

OpenClaw: auth bypass allows unauthorized focus state change

CVE-2026-53850
5.5
EPSS 0.1%
Auth BypassAgentFramework
openclawCWE-86233 ATLAS
MEDIUM

OpenClaw: exec allowlist bypass via command wrappers

CVE-2026-53848
4.3
EPSS 0.2%
Auth BypassCode ExecutionAgentFramework
openclawCWE-18433 ATLAS
MEDIUM

OpenClaw: privilege escalation via write scope bypass

CVE-2026-53847
5.4
EPSS 0.2%
Auth BypassAgent
openclawCWE-26633 ATLAS
MEDIUM

OpenClaw: hook bypass enables audit/policy evasion

CVE-2026-53845
4.3
EPSS 0.2%
Auth BypassData ExtractionAgentFramework
openclawCWE-69333 ATLAS
MEDIUM

OpenClaw: auth bypass exposes cross-session agent memory

CVE-2026-53844
6.5
EPSS 0.2%
Auth BypassData ExtractionPrivacy ViolationAgentFramework
openclawCWE-86234 ATLAS
MEDIUM

OpenClaw: XSS via unsafe links in exported session HTML

CVE-2026-53841
6.1
EPSS 0.2%
Code ExecutionSocial EngineeringData LeakageAgent
openclawCWE-8334 ATLAS
MEDIUM

LangGraph SQLite: deserialization RCE at checkpoint load

CVE-2026-48775
6.8
EPSS 0.2%
Code ExecutionSupply ChainFrameworkAgent
langgraphCWE-5024.1K4 ATLAS
MEDIUMEXPLOIT AVAIL

stable-diffusion.cpp: OOB read crash via crafted .ckpt file

CVE-2026-47748
5.5
EPSS 0.2%
Supply ChainDoSModelInference
CWE-1253 ATLAS
MEDIUM

n8n: webhook prototype pollution enables confused deputy

CVE-2026-54306
--
EPSS 0.3%
Auth BypassData LeakageCode ExecutionAgentFrameworkPlugin
n8nPatch: 2.26.2CWE-1321165 ATLAS
MEDIUM

n8n: unauthed webhook bypass hijacks AI agent workflows

CVE-2026-54308
--
EPSS 0.3%
Auth BypassCode ExecutionData ExtractionAgentFrameworkPlugin
n8nPatch: 2.26.2CWE-290165 ATLAS
MEDIUMEXPLOIT AVAIL

Langflow: unauth file read via Shareable Playground

CVE-2026-48520
6.1
EPSS 0.4%
Data ExtractionData LeakageAuth BypassFrameworkAgent
langflowPatch: 1.10.0CWE-735 ATLAS
MEDIUMEXPLOIT AVAIL

Langflow: path traversal enables arbitrary file write

CVE-2026-42867
6.5
EPSS 0.5%
Code ExecutionData LeakageSupply ChainFrameworkRAG
langflowPatch: 1.9.0CWE-223 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