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

96

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: PATH shadowing allowlist bypass on Windows

CVE-2026-100584
6.7
EPSS 0.1%
Code ExecutionAuth BypassAgentFramework
CWE-4264 ATLAS
MEDIUM

OpenClaw: authorization bypass leaks Discord guild metadata

CVE-2026-100583
4.3
EPSS 0.2%
Auth BypassData LeakageAgentPlugin
openclawCWE-86232 ATLAS
MEDIUM

OpenClaw: channel read allowlist bypass leaks chat data

CVE-2026-100582
6.5
EPSS 0.2%
Auth BypassData LeakageData ExtractionAgentPlugin
openclawCWE-86234 ATLAS
MEDIUM

OpenClaw iOS: cleartext Gateway credentials in UserDefaults

CVE-2026-100581
5.5
EPSS 0.1%
Data LeakageAuth BypassAgentAPI
openclawCWE-31234 ATLAS
MEDIUM

OpenClaw: SSRF via unvalidated video asset URLs

CVE-2026-100577
6.3
EPSS 0.1%
Supply ChainData LeakageAgentAPIPlugin
openclawCWE-91832 ATLAS
MEDIUM

OpenClaw: SSRF via browser wait predicates bypass

CVE-2026-100576
5.4
EPSS 0.2%
Data LeakageAuth BypassAgentFramework
openclawCWE-91833 ATLAS
MEDIUM

OpenClaw: SSRF via 0.0.0.0 bypass in trusted-host DNS

CVE-2026-100574
5.9
EPSS 0.2%
Data ExtractionData LeakageAgentFramework
openclawCWE-91832 ATLAS
MEDIUM

OpenClaw: pre-auth rate limit enables webhook DoS

CVE-2026-100572
5.3
EPSS 0.3%
DoSAgentAPI
openclawCWE-40032 ATLAS
MEDIUM

OpenClaw: SMS webhook rate-limit DoS drops Twilio callbacks

CVE-2026-100571
5.3
EPSS 0.3%
DoSAgentAPI
openclawCWE-40032 ATLAS
MEDIUM

OpenClaw: endpoint override leaks Azure Speech key

CVE-2026-100569
5.5
EPSS 0.1%
Data LeakageData ExtractionAgentPluginAPI
openclawCWE-52234 ATLAS
MEDIUM

OpenClaw LINE: group allowlist inherits DM allowFrom

CVE-2026-100566
6.5
EPSS 0.2%
Auth BypassData LeakageAgentPlugin
openclawCWE-86333 ATLAS
MEDIUM

OpenClaw: CSV formula injection in attendance export

CVE-2026-100564
5.4
EPSS 0.2%
Data ExtractionSocial EngineeringAgentPlugin
openclawCWE-123632 ATLAS
MEDIUM

OpenClaw: CSV formula injection in session export

CVE-2026-100563
5.4
EPSS 0.2%
Code ExecutionData LeakageAgentFramework
openclawCWE-123632 ATLAS
MEDIUM

OpenClaw: authorization bypass in sessions.create

CVE-2026-100562
5.4
EPSS 0.2%
Auth BypassData LeakageAgentAPIFramework
openclawCWE-86333 ATLAS
MEDIUM

OpenClaw: auth bypass lets WhatsApp group users switch models

CVE-2026-100556
6.3
EPSS 0.3%
Auth BypassPrivacy ViolationAgentFramework
openclawCWE-86332 ATLAS
MEDIUM

OpenClaw: Canvas HTTP auth persists after node revocation

CVE-2026-100554
4.2
EPSS 0.2%
Auth BypassData LeakageAgentFrameworkAPI
openclawCWE-61333 ATLAS
MEDIUM

OpenClaw: Feishu unpin bypasses cross-context policy

CVE-2026-100553
4.3
EPSS 0.2%
Auth BypassAgentPlugin
openclawCWE-86332 ATLAS
MEDIUM

OpenClaw: Teams allowlist bypass lets outsiders trigger agent

CVE-2026-100550
5.4
EPSS 0.2%
Auth BypassAgentPlugin
openclawCWE-86333 ATLAS
MEDIUM

OpenClaw: path traversal via QQBot voice filenames

CVE-2026-100549
5.4
EPSS 0.3%
Code ExecutionSupply ChainAgentPlugin
openclawCWE-2232 ATLAS
MEDIUM

OpenClaw: API key leak to fallback embedding provider

CVE-2026-100548
5.3
EPSS 0.3%
Data LeakageData ExtractionAgentAPIFramework
openclawCWE-20033 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