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 1961 results — Active exploitation
MEDIUMEXPLOIT AVAIL

NLTK: symlink escape allows arbitrary file read

CVE-2026-70626
6.2
EPSS 0.2%
Data LeakagePrivacy ViolationTraining DataFramework
nltkPatch: 3.9.4CWE-592.8K3 ATLAS
MEDIUMEXPLOIT AVAIL

Ollama: integer overflow in GGUF decoder causes DoS

CVE-2026-86289
4.3
EPSS 0.7%
DoSSupply ChainInferenceModel
ollamaCWE-1891.9K3 ATLAS
HIGHEXPLOIT AVAIL

Pterodactyl Panel: subuser escalation to console RCE

CVE-2026-86177
8.8
EPSS 0.6%
Auth BypassCode ExecutionFramework
CWE-862
HIGHEXPLOIT AVAIL

SiYuan: CookieKey leak enables session forgery

CVE-2026-72794
8.6
EPSS 0.3%
Auth BypassData LeakageAPI
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260725123945-77421530be4aCWE-5223.0K2 ATLAS
HIGHEXPLOIT AVAIL

CodeWhale: repo config silently enables shell RCE

CVE-2026-75911
7.8
EPSS 0.2%
Code ExecutionSupply ChainAgentPlugin
codewhalePatch: 0.8.64CWE-945 ATLAS
HIGHEXPLOIT AVAIL

DeepSeek-TUI: git_blame argument injection leaks files

CVE-2026-75912
7.4
EPSS 0.4%
Prompt InjectionData LeakagePrivacy ViolationAgentPlugin
codewhalePatch: 0.8.64CWE-884 ATLAS
HIGHEXPLOIT AVAIL

deepseek-tui: SSRF via DNS-pinning TOCTOU bypass

CVE-2026-75856
8.6
EPSS 0.5%
Data ExtractionAuth BypassAgentPlugin
codewhalePatch: 0.8.64CWE-9182 ATLAS
HIGHEXPLOIT AVAIL

deepseek-tui: js_execution leaks parent secrets to LLM

CVE-2026-75915
7.5
EPSS 0.7%
Data LeakagePrivacy ViolationCode ExecutionAgentPlugin
codewhalePatch: 0.8.64CWE-2004 ATLAS
HIGHEXPLOIT AVAIL

CodeWhale: shell approval bypass via interactive tool

CVE-2026-75857
7.0
EPSS 0.2%
Prompt InjectionCode ExecutionAuth BypassAgent
codewhalePatch: 0.8.64CWE-2693 ATLAS
HIGHEXPLOIT AVAIL

CodeWhale: arbitrary file read via instructions field

CVE-2026-75859
7.5
EPSS 0.5%
Supply ChainData LeakagePrivacy ViolationAgentFramework
codewhalePatch: 0.8.64CWE-225 ATLAS
HIGHEXPLOIT AVAIL

CodeWhale: symlink traversal leaks files via vision API

CVE-2026-75914
7.5
EPSS 0.5%
Data LeakagePrompt InjectionAuth BypassAgentPluginInference
codewhalePatch: 0.8.64CWE-224 ATLAS
HIGHEXPLOIT AVAIL

ms-swift: unauth SSRF via multimodal media URLs

CVE-2026-85686
7.5
EPSS 0.5%
Code ExecutionData LeakageInferenceAPI
ms-swiftCWE-91862 ATLAS
HIGHEXPLOIT AVAIL

LLaMA-Factory: SSRF guard bypass via redirect/DNS rebind

CVE-2026-85673
7.5
EPSS 0.5%
Auth BypassData ExtractionAPIInference
llama-factoryCWE-9183 ATLAS
MEDIUMEXPLOIT AVAIL

tokenizers: malformed vocab crashes process (DoS)

CVE-2026-85670
6.5
EPSS 0.5%
DoSSupply ChainInferenceTraining Data
tokenizersCWE-78716.9K3 ATLAS
HIGHEXPLOIT AVAIL

OGX/Llama Stack: SSRF via MCP tool server_url

CVE-2026-85666
7.5
EPSS 0.7%
Data LeakageAuth BypassAgentAPIPlugin
llama-stackCWE-918143 ATLAS
MEDIUMEXPLOIT AVAIL

SiYuan: auth bypass leaks hidden notebook files

CVE-2026-85578
6.5
EPSS 0.4%
Auth BypassData LeakageRAG
CWE-8622 ATLAS
MEDIUMEXPLOIT AVAIL

SiYuan: broken authz leaks DB schema & block IDs

CVE-2026-72800
5.8
EPSS 0.3%
Auth BypassData LeakageAPI
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260724103335-f36331956ae9CWE-8623.0K2 ATLAS
MEDIUMEXPLOIT AVAIL

SiYuan: auth bypass exposes private notebook content

CVE-2026-72805
5.8
EPSS 0.3%
Auth BypassData LeakagePrivacy ViolationRAGAPI
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260723163028-931ba693375eCWE-8623.0K1 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: WebSocket leak bypasses publish access control

CVE-2026-72810
8.6
EPSS 0.5%
Auth BypassData LeakagePrivacy ViolationPlugin
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260723013612-ba948639d7f6CWE-8623.0K1 ATLAS
MEDIUMEXPLOIT AVAIL

SiYuan: broken auth on refreshBacklink enables DoS

CVE-2026-72812
6.5
EPSS 0.4%
Auth BypassDoSFramework
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260723002528-7d273c271ce1CWE-8623.0K2 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