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

JetBrains Datalore: argument injection allows sidecar command execution

CVE-2026-123281
7.5
Code ExecutionFrameworkPlugin
CWE-882 ATLAS
HIGH

AG2: shell filter bypass via newline enables RCE

CVE-2026-113663
8.8
Code ExecutionPrompt InjectionAgentFrameworkPlugin
autogenCWE-78164 ATLAS
HIGH

Codex Desktop Windows: argument injection runs code

CVE-2026-110930
8.0
Code ExecutionSupply ChainAgentFramework
Codex Desktop for Windows1.8K3 ATLAS
HIGH

ESPectre: unsafe NPZ pickle load allows code execution

CVE-2026-102739
7.8
Code ExecutionSupply ChainModel PoisoningTraining DataFramework
CWE-5024 ATLAS
HIGH

H2O: access-log buffer overflow crashes HTTP server

CVE-2026-55368
8.1
EPSS 0.3%
DoSInferenceFramework
CWE-7872 ATLAS
HIGH

H2O: unbounded CONNECT-UDP capsule buffering causes DoS

CVE-2026-55367
7.5
EPSS 0.3%
DoSFrameworkInference
h2oCWE-770272 ATLAS
HIGH

Mistral Vibe: RCE via repo-configured gpg.program

CVE-2026-122135
8.8
EPSS 0.5%
Code ExecutionSupply ChainAgentFramework
mistral-vibe4734 ATLAS
HIGH

Mistral Vibe: Git filter RCE on repo open

CVE-2026-122134
8.8
EPSS 0.5%
Code ExecutionSupply ChainAgentFramework
mistral-vibe4734 ATLAS
HIGH

Mistral Vibe: untrusted git.exe path allows RCE on Windows

CVE-2026-122133
8.8
EPSS 0.4%
Code ExecutionSupply ChainAgentFramework
mistral-vibe4734 ATLAS
HIGH

Stanza: unsafe pickle in lemma model load enables RCE

CVE-2026-115878
7.8
EPSS 0.6%
Code ExecutionSupply ChainFrameworkModel
stanzaPatch: 1.15.0CWE-9426.1K5 ATLAS
HIGH

Claude Code: TOCTOU symlink race lets sandbox escape file write

CVE-2026-88968
--
EPSS 0.3%
Code ExecutionSupply ChainAgentPlugin
claude-code4 ATLAS
HIGH

Elastic Docker images: compromised eMudhra CAs enable TLS MITM

CVE-2026-115714
7.4
EPSS 0.2%
Supply ChainData LeakageFramework
1 ATLAS
HIGH

Label Studio: SSRF in export leaks internal data, API token

CVE-2026-121561
7.7
EPSS 0.4%
Data ExtractionAuth BypassData LeakageFrameworkTraining Data
label-studio25 ATLAS
HIGH

json-glib: infinite loop in JSONPath slice causes DoS

CVE-2026-120194
7.5
DoSFrameworkInference
rhoai/odh-mlflow-operator-rhel96952 ATLAS
HIGH

node-forge: PKCS#12 MAC bypass via zero iteration count

CVE-2026-118782
7.5
EPSS 0.1%
Auth BypassSupply ChainFrameworkAPI
node-forgePatch: 1.4.1CWE-3546.3K2 ATLAS
HIGH

fickling: safe-import trust bypass allows pickle RCE

CVE-2026-16760
8.8
EPSS 0.5%
Code ExecutionSupply ChainFrameworkModel
6 ATLAS
HIGH

fickling: dotted-name bypass lets malicious pickle pass scan

CVE-2026-118938
8.8
EPSS 0.5%
Code ExecutionSupply ChainFrameworkModel
fickling625 ATLAS
HIGH

RAGFlow: missing authz lets users run others' agents

CVE-2026-119337
7.1
EPSS 0.3%
Auth BypassData LeakageRAGAgentAPI
CWE-8624 ATLAS
HIGH

Flowise: sandbox escape allows authenticated RCE

CVE-2026-119978
8.5
EPSS 0.3%
Code ExecutionFrameworkAgent
FlowiseCWE-7494 ATLAS
HIGHEXPLOIT AVAIL

MONAI: code execution via Auto3DSeg algo_object.json

CVE-2026-119578
7.8
EPSS 0.6%
Code ExecutionSupply ChainFrameworkTraining Data
monaiCWE-4701283 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