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

95

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
HIGHEXPLOIT AVAIL

Qwen-Agent: path traversal in doc parser leaks files

CVE-2026-82275
7.5
EPSS 0.5%
Data ExtractionData LeakageAgentPlugin
CWE-223 ATLAS
HIGHEXPLOIT AVAIL

Qwen-Agent: unauth SSRF via document URL parser

CVE-2026-82268
7.5
EPSS 0.5%
Data ExtractionData LeakageAgentPlugin
CWE-9183 ATLAS
HIGHEXPLOIT AVAIL

9router: Host-header spoof bypasses auth, enables SSRF

CVE-2026-55641
8.2
EPSS 0.3%
Auth BypassData LeakageData ExtractionAPIFramework
9routerPatch: 0.5.2CWE-2901.8K4 ATLAS
HIGHEXPLOIT AVAIL

9router: /codex bypass exposes LLM proxy credentials

CVE-2026-55638
8.6
EPSS 6.6%
Auth BypassPrivacy ViolationAPIFrameworkInference
9routerPatch: 0.5.2CWE-8621.8K3 ATLAS
HIGH

vLLM: unbounded media URLs cause memory-exhaustion DoS

CVE-2026-37237
7.5
EPSS 0.7%
DoSInference
vllm943 ATLAS
HIGH

Spring AI: predictable ONNX cache path enables model swap

CVE-2026-47852
7.5
EPSS 0.3%
Supply ChainCode ExecutionFrameworkModelInference
3 ATLAS
HIGHEXPLOIT AVAIL

Penpot: stored XSS in comments enables session takeover

CVE-2026-47665
8.7
EPSS 0.4%
Code ExecutionData LeakageFramework
CWE-79
HIGHEXPLOIT AVAIL

Pterodactyl Wings: SFTP quota bypass causes node-wide DoS

CVE-2026-61617
7.7
EPSS 0.4%
DoSInference
CWE-4001 ATLAS
HIGHEXPLOIT AVAIL

Cohere North: WebSocket leak exposes session data

CVE-2025-61164
7.5
EPSS 0.3%
Data LeakageAuth BypassAgentAPI
3 ATLAS
HIGH

Cohere North AI: IDOR allows overwriting any user record

CVE-2025-61162
7.5
EPSS 0.4%
Auth BypassPrivacy ViolationAPIAgent
2 ATLAS
HIGH

LibreNMS: stored XSS via unescaped SNMP/syslog data

GHSA-7w8c-qgxg-m7jx
7.1
Code ExecutionData LeakageFramework
librenms/librenmsPatch: 26.5.0CWE-79514
HIGHEXPLOIT AVAIL

Chainlit: unauth SSRF via MCP url/header injection

CVE-2026-45019
7.2
EPSS 0.4%
Auth BypassData ExtractionFrameworkPluginAgent
chainlitPatch: 2.12.0CWE-918413 ATLAS
HIGH

Vocos: RCE via unrestricted class loading in model config

CVE-2026-79784
8.8
EPSS 0.6%
Supply ChainCode ExecutionModelInference
CWE-4704 ATLAS
HIGHEXPLOIT AVAIL

mcp-shell: insecure defaults allow full shell RCE

CVE-2026-55580
--
EPSS 0.2%
Code ExecutionPrompt InjectionAgentPlugin
CWE-784 ATLAS
HIGHEXPLOIT AVAIL

mcp-shell: bash allowlist bypass grants RCE, no auth

CVE-2026-55581
8.4
EPSS 0.5%
Code ExecutionAuth BypassAgentPlugin
CWE-783 ATLAS
HIGHEXPLOIT AVAIL

mcp-shell: secure mode bypass via git alias RCE

CVE-2026-55582
8.4
EPSS 0.3%
Code ExecutionAuth BypassAgentPlugin
CWE-784 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: Origin bypass CSRF enables prompt injection

CVE-2026-55532
7.6
EPSS 0.2%
Auth BypassPrompt InjectionAgentPlugin
PraisonAIPatch: 4.6.58CWE-34615 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: auth fail-open lets unauthenticated recipe execution

CVE-2026-55533
8.2
EPSS 0.5%
Auth BypassCode ExecutionAgentAPI
PraisonAIPatch: 4.6.58CWE-28713 ATLAS
HIGH

PraisonAI: no-auth Jobs API allows arbitrary agent runs

CVE-2026-55539
8.6
EPSS 0.6%
Auth BypassData LeakageDoSAgentAPIFramework
PraisonAIPatch: 4.6.58CWE-30613 ATLAS
HIGH

PraisonAI: path traversal in agent memory allows arbitrary file write

CVE-2026-55527
7.1
EPSS 0.5%
Code ExecutionDoSAgentFramework
praisonaiagentsPatch: 1.6.58CWE-22203 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