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 1908 results — High severity
HIGH

OpenClaw: case-sensitivity bypass enables persistent RCE

CVE-2026-100580
8.8
EPSS 0.3%
Code ExecutionPrompt InjectionAgentFrameworkPlugin
openclawCWE-17835 ATLAS
HIGH

OpenClaw: spoofed requester identity bypasses channel authz

CVE-2026-100579
7.6
EPSS 0.2%
Auth BypassAgentFrameworkAPI
openclawCWE-63933 ATLAS
HIGH

OpenClaw: owner-only tools exposed via chat.send

CVE-2026-100578
7.6
EPSS 0.2%
Auth BypassPrompt InjectionAgentFrameworkAPI
openclawCWE-26934 ATLAS
HIGH

OpenClaw: Slack sender allowlist bypass in group DMs

CVE-2026-100575
8.8
EPSS 0.3%
Auth BypassData LeakageAgentPlugin
openclawCWE-86233 ATLAS
HIGH

OpenClaw: env injection via workspace .env allows code exec

CVE-2026-100570
7.8
EPSS 0.1%
Code ExecutionSupply ChainAgentFramework
openclawCWE-8833 ATLAS
HIGH

OpenClaw: broken access control exposes cron command jobs

CVE-2026-100568
8.3
EPSS 0.3%
Auth BypassData LeakageCode ExecutionAgentFramework
openclawCWE-20034 ATLAS
HIGH

OpenClaw: DNS rebinding bypasses CDP SSRF protection

CVE-2026-100567
8.2
EPSS 0.3%
Auth BypassData LeakageAgentFrameworkAPI
openclawCWE-91833 ATLAS
HIGH

OpenClaw: exec approval bypass enables host command execution

CVE-2026-100561
8.0
EPSS 0.2%
Auth BypassCode ExecutionAgentFramework
openclawCWE-8834 ATLAS
HIGH

OpenClaw: persistent exec approval bypass via path-only grants

CVE-2026-100560
7.5
EPSS 0.6%
Auth BypassCode ExecutionAgentFramework
openclawCWE-86334 ATLAS
HIGH

OpenClaw: escaped-newline parsing bypasses exec allowlist

CVE-2026-100559
8.0
EPSS 0.2%
Code ExecutionAuth BypassAgentFramework
openclawCWE-7834 ATLAS
HIGH

OpenClaw: WebSocket upgrade socket exhaustion DoS

CVE-2026-100558
7.5
EPSS 0.3%
DoSAgentAPI
openclawCWE-40032 ATLAS
HIGH

OpenClaw: skill dispatch authz bypass exposes owner tools

CVE-2026-100557
8.3
EPSS 0.2%
Auth BypassData LeakageAgentPluginFramework
openclawCWE-86334 ATLAS
HIGH

OpenClaw: DNS rebinding SSRF in Synology Chat attachments

CVE-2026-100555
7.1
EPSS 0.2%
Data LeakageData ExtractionAgentPluginFramework
openclawCWE-91832 ATLAS
HIGH

OpenClaw: Codex runtime bypasses per-chat tool policy

CVE-2026-100552
8.8
EPSS 0.3%
Auth BypassCode ExecutionAgentFrameworkPlugin
openclawCWE-86333 ATLAS
HIGH

OpenClaw iOS: TLS pin bypass leaks Gateway credentials

CVE-2026-100551
8.3
EPSS 0.2%
Auth BypassData LeakageSocial EngineeringAgentFrameworkAPI
openclawCWE-29534 ATLAS
HIGH

OpenClaw: authz bypass in voice-call exposes owner tools

CVE-2026-100544
8.8
EPSS 0.2%
Auth BypassCode ExecutionAgentPluginFramework
openclawCWE-86234 ATLAS
HIGH

OpenClaw: config hashes enable offline password cracking

CVE-2026-100543
7.5
EPSS 0.3%
Auth BypassData LeakageAgentAPIFramework
openclawCWE-20034 ATLAS
HIGH

OpenClaw Matrix: case-folding auth bypass via ID collision

CVE-2026-100541
7.5
EPSS 0.3%
Auth BypassSocial EngineeringAgentPluginFramework
openclawCWE-17833 ATLAS
HIGH

OpenClaw: session-memory flaw enables agent privilege escalation

CVE-2026-100535
7.5
EPSS 0.3%
Prompt InjectionAuth BypassCode ExecutionAgentFramework
openclawCWE-86334 ATLAS
HIGH

OpenClaw: exec approval reuse across directories

CVE-2026-100530
7.3
EPSS 0.2%
Auth BypassCode ExecutionAgentFramework
openclawCWE-86333 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