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

vLLM: audio decode DoS via NanoNemotronVL video input

CVE-2026-90554
7.5
EPSS 0.2%
DoSInferenceModel
vllmCWE-400943 ATLAS
HIGH

vLLM: RCE bypasses trust_remote_code model safeguard

CVE-2026-90553
7.8
EPSS 0.3%
Supply ChainCode ExecutionInferenceModel
vllmCWE-94944 ATLAS
HIGHEXPLOIT AVAIL

Flowise: IDOR in abort API enables agent DoS

CVE-2026-90535
7.5
EPSS 0.5%
Auth BypassDoSAgentAPI
flowiseCWE-8622 ATLAS
HIGHEXPLOIT AVAIL

Mockoon: unauth admin API leaks secrets, hijacks mocks

CVE-2026-59148
8.8
EPSS 0.3%
Auth BypassData LeakageDoSAPI
@mockoon/cliPatch: 9.7.0CWE-3061.9K2 ATLAS
HIGHEXPLOIT AVAIL

Headroom: CSWSH bypass allows unauthenticated LLM abuse

CVE-2026-71416
8.8
EPSS 0.2%
Auth BypassData LeakageAPIInference
headroom-aiPatch: 0.35.0CWE-2871.8K3 ATLAS
HIGHEXPLOIT AVAIL

Traefik: HTTP routing desync enables auth/log bypass

CVE-2026-88009
--
EPSS 0.4%
Auth BypassData LeakageInferenceAPIAgent
github.com/traefik/traefik/v2Patch: 2.11.57CWE-44421 ATLAS
HIGH

Langflow: authenticated path traversal enables RCE

CVE-2026-84889
8.8
EPSS 0.9%
Code ExecutionFrameworkAgent
langflowCWE-223 ATLAS
HIGH

Langflow: MCP stdio tool bypasses RCE lockdown

CVE-2026-81941
8.8
EPSS 0.6%
Code ExecutionAuth BypassAgentFramework
langflowCWE-2844 ATLAS
HIGH

Langflow: RCE via unsanitized flow display names

CVE-2026-81940
8.8
EPSS 0.8%
Code ExecutionFrameworkAgent
CWE-943 ATLAS
HIGH

Langflow: stale API keys survive user deactivation

CVE-2026-81268
8.1
EPSS 0.4%
Auth BypassData LeakageFrameworkAgentAPI
langflowCWE-6133 ATLAS
HIGH

Langflow: unauthenticated SSRF exposes internal resources

CVE-2026-81265
7.5
EPSS 0.4%
Data ExtractionPrivacy ViolationFrameworkAgent
langflowCWE-9182 ATLAS
HIGH

IBM Langflow: SSRF exposes internal network resources

CVE-2026-81213
8.6
EPSS 0.5%
Data LeakageData ExtractionFrameworkAgent
langflowCWE-9182 ATLAS
HIGH

Langflow: broken authz on components enables RCE

CVE-2026-81211
8.8
EPSS 0.6%
Code ExecutionAuth BypassFrameworkAgentPlugin
langflowCWE-8623 ATLAS
HIGH

Langflow: RCE via incomplete env var blocklist

CVE-2026-79742
8.8
EPSS 0.9%
Code ExecutionData LeakageFrameworkAgent
langflowCWE-943 ATLAS
HIGH

Langflow: RCE via unsanitized MCP stdio server args

CVE-2026-78575
8.8
EPSS 0.8%
Code ExecutionFrameworkAgentPlugin
langflowCWE-783 ATLAS
HIGH

Langflow: authenticated RCE via unguarded eval()

CVE-2026-78571
8.8
EPSS 0.8%
Code ExecutionFrameworkAgent
langflowCWE-943 ATLAS
HIGH

Langflow: incomplete denylist enables authenticated RCE

CVE-2026-78569
8.8
EPSS 0.7%
Code ExecutionFrameworkAgent
langflowCWE-783 ATLAS
HIGH

Langflow: RCE via scanner bypass in custom components

CVE-2026-76059
8.8
EPSS 0.7%
Code ExecutionSupply ChainFrameworkAgent
langflowCWE-6933 ATLAS
HIGH

mistral.rs: unbounded media fetch enables DoS

GHSA-m3wp-48jr-vr4g
7.5
DoSInferenceAPI
mistralrs-server-corePatch: 0.8.18CWE-4001.8K3 ATLAS
HIGH

mistral.rs: SSRF & file-read via image/audio URLs

GHSA-wfgq-w7cq-qj7j
7.2
Data ExtractionDoSPrivacy ViolationInferenceAPI
mistralrs-server-corePatch: 0.8.18CWE-73943 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