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 306 results — High severity, Active exploitation, has patch
HIGHEXPLOIT AVAIL

Rembg: unauthenticated path traversal leaks files

CVE-2026-115924
8.6
EPSS 0.4%
Data ExtractionSupply ChainData LeakageFrameworkAPIInference
rembgPatch: 2.0.82CWE-221.1K5 ATLAS
HIGHEXPLOIT AVAIL

virtualenv: GBK quote bypass in xonsh activation enables RCE

CVE-2026-113718
--
EPSS 0.2%
Code ExecutionSupply ChainFramework
virtualenvPatch: 21.14.9CWE-946.3K3 ATLAS
HIGHEXPLOIT AVAIL

virtualenv: prompt injection enables shell command execution

CVE-2026-113723
--
EPSS 0.2%
Code ExecutionSupply ChainFramework
virtualenvPatch: 21.14.9CWE-786.3K3 ATLAS
HIGHEXPLOIT AVAIL

filelock: SQLite symlink redirect enables file overwrite

CVE-2026-112940
7.1
EPSS 0.2%
Supply ChainDoSFrameworkTraining Data
filelockPatch: 4.2.1CWE-596.3K2 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: WebSocket auth bypass leaks live event stream

CVE-2026-73054
7.5
EPSS 0.4%
Auth BypassData LeakageFrameworkAPI
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260731131820-67bc300b6ea6CWE-2873.0K3 ATLAS
HIGHEXPLOIT AVAIL

obsidian-tc: HITL approval bypass runs destructive tools

CVE-2026-115477
--
EPSS 0.4%
Auth BypassAgentPlugin
obsidian-tcPatch: 1.31.4CWE-28523 ATLAS
HIGHEXPLOIT AVAIL

virtualenv: shell injection in launcher path runs code

CVE-2026-113722
7.8
EPSS 0.3%
Code ExecutionSupply ChainFramework
virtualenvPatch: 21.14.9CWE-786.3K3 ATLAS
HIGHEXPLOIT AVAIL

MLflow: path traversal allows arbitrary file write

CVE-2026-53995
8.2
EPSS 0.6%
Auth BypassSupply ChainFrameworkAPI
mlflowPatch: 3.17.2CWE-226952 ATLAS
HIGHEXPLOIT AVAIL

Nginx UI: missing 2FA step-up on admin mutation routes

CVE-2026-84315
8.3
EPSS 0.3%
Auth BypassAPIFramework
github.com/0xJacky/Nginx-UIPatch: 1.9.10-0.20260703131214-23d1934099b0CWE-8621.8K2 ATLAS
HIGHEXPLOIT AVAIL

Guava: unbounded deserialization allocation causes DoS

CVE-2026-102554
5.9
EPSS 0.4%
DoSFrameworkInference
com.google.guava:guavaPatch: 33.7.2CWE-4002 ATLAS
HIGHEXPLOIT AVAIL

Coraza WAF: ARGS limit silent drop bypasses WAF rules

CVE-2026-41510
7.2
EPSS 0.4%
DoSAuth BypassAPIFramework
github.com/corazawaf/coraza/v3Patch: 3.8.1CWE-6936.3K3 ATLAS
HIGHEXPLOIT AVAIL

vm2: unhandled Promise rejection in construct trap kills host

CVE-2026-100722
8.6
EPSS 0.3%
DoSFrameworkAgentPlugin
vm2Patch: 3.12.2CWE-2483.0K3 ATLAS
HIGHEXPLOIT AVAIL

fsspec: Jinja2 SSTI in Kerchunk refs allows RCE

CVE-2026-104851
8.8
EPSS 0.5%
Code ExecutionSupply ChainFrameworkTraining Data
fsspecPatch: 2026.6.0CWE-943614 ATLAS
HIGHEXPLOIT AVAIL

vm2: unhandled host Promise rejection crashes Node host

CVE-2026-92954
8.6
EPSS 0.5%
DoSFrameworkAgentPlugin
vm2Patch: 3.11.8CWE-2483.0K3 ATLAS
HIGHEXPLOIT AVAIL

Langflow: X-Forwarded-For spoof lets users write MCP config

CVE-2026-105741
7.1
EPSS 0.2%
Auth BypassSupply ChainFrameworkAgentPlugin
langflowPatch: 1.10.3CWE-2903 ATLAS
HIGHEXPLOIT AVAIL

Langflow: cross-tenant file read via MCP resources/read

CVE-2026-105699
--
EPSS 0.3%
Data LeakageAuth BypassData ExtractionFrameworkAgentRAG
langflowPatch: 1.9.1CWE-6394 ATLAS
HIGHEXPLOIT AVAIL

Langflow: code injection in validate/code enables RCE

CVE-2026-51886
8.8
EPSS 0.6%
Code ExecutionFrameworkAgent
langflowPatch: 1.10.1CWE-944 ATLAS1 incident
HIGHEXPLOIT AVAIL

9router: DNS rebinding SSRF in image prefetch

CVE-2026-56676
7.4
EPSS 0.2%
Data ExtractionData LeakageInferenceAPIFramework
9routerPatch: 0.5.2CWE-3671.9K3 ATLAS
HIGHEXPLOIT AVAIL

mcp-atlassian: arbitrary server file upload via path

CVE-2026-77247
--
EPSS 0.4%
Data ExtractionData LeakageAgentPlugin
mcp-atlassianPatch: 0.22.0CWE-7324 ATLAS
HIGHEXPLOIT AVAIL

mcp-atlassian: path traversal enables arbitrary file read

CVE-2026-77262
8.6
EPSS 0.6%
Data ExtractionData LeakageAuth BypassAgentPluginAPI
mcp-atlassianPatch: 0.22.0CWE-2226 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