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 1431 results — has patch
HIGH

mcp-atlassian: SSRF via unvalidated redirects

CVE-2026-77261
7.1
EPSS 0.4%
Data ExtractionData LeakageAgentPluginAPI
mcp-atlassianPatch: 0.22.0CWE-91823 ATLAS
HIGHEXPLOIT AVAIL

MCP Atlassian: path traversal in upload_attachment

CVE-2026-77260
--
EPSS 0.4%
Data ExtractionData LeakageAgentPlugin
mcp-atlassianPatch: 0.22.0CWE-2225 ATLAS
HIGHEXPLOIT AVAIL

MCP Atlassian: path traversal enables code execution

CVE-2026-77271
--
EPSS 0.6%
Code ExecutionSupply ChainAgentPluginFramework
mcp-atlassianPatch: 0.22.0CWE-2224 ATLAS
HIGHEXPLOIT AVAIL

MCP Atlassian: missing authz lets clients call hidden tools

CVE-2026-77243
8.8
EPSS 0.5%
Auth BypassData LeakageAgentPluginAPI
mcp-atlassianPatch: 0.22.0CWE-86224 ATLAS
HIGHEXPLOIT AVAIL

MCP Atlassian: project/space filter bypass exposes data

CVE-2026-77251
--
EPSS 0.3%
Data LeakageAuth BypassData ExtractionAgentPluginAPI
mcp-atlassianPatch: 0.22.0CWE-18424 ATLAS
HIGHEXPLOIT AVAIL

MCP Atlassian: SSRF via header URLs bypasses prior fix

CVE-2026-77267
--
EPSS 0.3%
Data ExtractionAuth BypassAgentPluginAPI
mcp-atlassianPatch: 0.22.0CWE-91823 ATLAS
MEDIUMEXPLOIT AVAIL

MCP Atlassian: cleartext OAuth token file readable locally

CVE-2026-77250
6.1
EPSS 0.1%
Data LeakageAuth BypassAgentPlugin
mcp-atlassianPatch: 0.22.0CWE-31224 ATLAS
CRITICAL

MCP Atlassian: unauthenticated access to operator Jira/Confluence

CVE-2026-77244
10.0
EPSS 0.3%
Auth BypassData ExtractionAgentPluginAPI
mcp-atlassianPatch: 0.22.0CWE-28725 ATLAS
MEDIUMEXPLOIT AVAIL

MCP Atlassian: DNS-rebinding SSRF exposes internal services

CVE-2026-77265
5.9
EPSS 0.3%
Data LeakageAuth BypassAgentPluginAPI
mcp-atlassianPatch: 0.22.0CWE-91823 ATLAS
MEDIUMEXPLOIT AVAIL

MCP Atlassian: path traversal in attachment upload leaks files

CVE-2026-77270
6.5
EPSS 0.5%
Data ExtractionData LeakagePrompt InjectionAgentPluginFramework
mcp-atlassianPatch: 0.22.0CWE-2225 ATLAS
HIGHEXPLOIT AVAIL

MCP Atlassian: path traversal exposes server files

CVE-2026-77258
7.7
EPSS 0.4%
Data ExtractionData LeakageAgentPlugin
mcp-atlassianPatch: 0.22.0CWE-2224 ATLAS
HIGHEXPLOIT AVAIL

mcp-atlassian: SSRF via backslash URL parsing confusion

CVE-2026-77274
--
EPSS 0.3%
Data LeakageAuth BypassAgentPluginAPI
mcp-atlassianPatch: 0.22.0CWE-91823 ATLAS
MEDIUMEXPLOIT AVAIL

LightRAG: error messages leak paths and DB credentials

CVE-2026-85709
5.3
EPSS 0.4%
Data LeakageData ExtractionRAGAPIFramework
lightrag-hkuPatch: 1.5.5CWE-2091.8K4 ATLAS
HIGH

vLLM: unbounded P2P KV sessions crash EngineCore (DoS)

CVE-2026-94624
7.5
EPSS 0.4%
DoSInferenceFramework
vllmPatch: 0.32.0CWE-770943 ATLAS
HIGH

NotebookLM MCP: path traversal enables arbitrary file write

CVE-2026-61647
--
EPSS 0.4%
Supply ChainCode ExecutionPrompt InjectionPluginAgentAPI
@roomi-fields/notebooklm-mcpPatch: 2.0.3CWE-223.0K4 ATLAS
HIGHEXPLOIT AVAIL

ToolHive: default network profile enables MCP lateral movement

CVE-2026-58197
8.8
EPSS 0.4%
Auth BypassData ExtractionCode ExecutionAgentPluginFramework
github.com/stacklok/toolhivePatch: 0.30.1CWE-2841.9K5 ATLAS
HIGH

lmdeploy: URL parser mismatch enables SSRF bypass

GHSA-39wr-7q6h-cf68
7.5
Data ExtractionAuth BypassInferenceAPI
lmdeployPatch: 0.15.0CWE-43613 ATLAS
HIGHEXPLOIT AVAIL

LMDeploy: eval() injection via malicious model config

CVE-2026-33625
8.8
EPSS 0.4%
Code ExecutionSupply ChainInferenceFrameworkModel
lmdeployPatch: 0.12.3CWE-40015 ATLAS
CRITICAL

LMDeploy: pickle deserialization RCE in DistServe

CVE-2025-66455
9.8
EPSS 1.3%
Code ExecutionAuth BypassInferenceAPIFramework
lmdeployPatch: 0.16.0CWE-50214 ATLAS
HIGHEXPLOIT AVAIL

Grav CMS: callable-array bypass enables authenticated RCE

CVE-2026-72819
8.8
EPSS 0.9%
Code ExecutionFramework
getgrav/gravPatch: 2.0.13CWE-945144 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