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 983 results — Medium severity, no patch
MEDIUMEXPLOIT AVAIL

ckan-mcp-server: cache key collision enables poisoning

CVE-2026-73846
6.5
EPSS 0.2%
Prompt InjectionAgentPlugin
CWE-3452 ATLAS
MEDIUM

n8n: IDOR exposes workflow data across projects

CVE-2026-85173
--
EPSS 0.3%
Auth BypassData LeakagePrivacy ViolationAgentAPI
n8n163 ATLAS
MEDIUM

n8n: SSRF bypass via uri/url validation mismatch

CVE-2026-85172
--
EPSS 0.3%
Auth BypassData LeakageAgentPlugin
n8nCWE-918162 ATLAS
MEDIUM

n8n: query injection turns lookup into full DB read

CVE-2026-85167
--
EPSS 0.4%
Data ExtractionData LeakageAuth BypassAgentPlugin
n8nCWE-943162 ATLAS
MEDIUM

InsydeH2O UEFI: buffer overflow in PlatformLangCodes var

CVE-2021-43614
6.7
EPSS 0.2%
DoSInference
InsydeH2O271 ATLAS
MEDIUM

InsydeH2O UEFI: password hashes exposed, privesc risk

CVE-2021-43613
6.5
EPSS 0.1%
Data LeakageAuth BypassInference
InsydeH2O271 ATLAS
MEDIUM

APM Server: memory-exhaustion DoS via source maps

CVE-2026-78594
4.9
EPSS 0.5%
DoSFramework
Apm Server1 ATLAS
MEDIUM

Kibana: missing authz leaks APM server credentials

CVE-2026-78608
6.5
EPSS 0.4%
Auth BypassData LeakagePluginAPI
1 ATLAS
MEDIUM

Filament: stale TOTP code stays valid, bypassing MFA reuse block

CVE-2026-84306
6.5
EPSS 0.4%
Auth BypassFramework
CWE-294
MEDIUMEXPLOIT AVAIL

pdfme: XSS via unsanitized i18n labels in Designer

CVE-2026-82865
4.4
EPSS 0.2%
Code ExecutionData LeakageFramework
CWE-792 ATLAS
MEDIUMEXPLOIT AVAIL

browser-use web-ui: stores LLM API keys in cleartext

CVE-2026-82640
5.5
EPSS 0.1%
Data LeakagePrivacy ViolationAgentAPI
CWE-3124 ATLAS
MEDIUMEXPLOIT AVAIL

browser-use: arbitrary directory creation via paths

CVE-2026-82637
5.3
EPSS 0.4%
Auth BypassDoSAgentFramework
browser-useCWE-73751 ATLAS
MEDIUMEXPLOIT AVAIL

ash_paper_trail: sensitive fields leak in version logs

CVE-2026-75847
--
EPSS 0.1%
Data LeakagePrivacy ViolationFramework
1 ATLAS
MEDIUM

Formwork: stored XSS via unescaped Referer header in stats

CVE-2026-82451
6.1
EPSS 0.4%
Auth BypassData LeakageFramework
CWE-79
MEDIUM

Langflow: authz flaw lets users run others' AI flows

CVE-2026-19294
6.5
EPSS 0.3%
Auth BypassData LeakageFrameworkAgent
langflowCWE-6394 ATLAS
MEDIUM

Langflow: SSRF lets authenticated users probe internal network

CVE-2026-18545
4.3
EPSS 0.3%
Auth BypassData ExtractionFrameworkAgent
langflowCWE-9182 ATLAS
MEDIUMEXPLOIT AVAIL

Chainlit: IDOR lets users tamper with others' feedback

CVE-2026-82290
5.3
EPSS 0.3%
Auth BypassFrameworkTraining Data
chainlitCWE-639412 ATLAS
MEDIUM

libsolv: OOB write in .solv cache causes tool crash

CVE-2026-82327
5.5
DoSFramework
rhoai/odh-mlflow-operator-rhel96951 ATLAS
MEDIUM

FFmpeg: heap overflow via crafted TDSC cursor in video

CVE-2026-18393
5.4
EPSS 0.4%
Code ExecutionDoSInference
rhoai/odh-vllm-gaudi-rhel9942 ATLAS
MEDIUMEXPLOIT AVAIL

crewai-tools: SQLi in NL2SQLTool allows DB compromise

CVE-2026-37009
6.5
EPSS 0.4%
Code ExecutionData ExtractionAgentPlugin
3 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