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
3,590

AI/ML CVEs Tracked

481

Critical

95

New This Week

24

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 800 results — High severity, Active exploitation
HIGH EXPLOIT AVAIL

NLTK: SSRF bypass via proxy-handler downgrade

CVE-2026-78682
--
EPSS 0.3%
Data Leakage Supply Chain Framework Training Data
nltk Patch: 3.10.3 CWE-441 2 2 ATLAS
HIGH EXPLOIT AVAIL

Pterodactyl Panel: subuser escalation to console RCE

CVE-2026-86177
8.8
EPSS 0.3%
Auth Bypass Code Execution Framework
CWE-862
HIGH EXPLOIT AVAIL

SiYuan: CookieKey leak enables session forgery

CVE-2026-72794
8.6
EPSS 0.2%
Auth Bypass Data Leakage API
github.com/siyuan-note/siyuan/kernel Patch: 0.0.0-20260725123945-77421530be4a CWE-522 3.1K 2 ATLAS
HIGH EXPLOIT AVAIL

CodeWhale: repo config silently enables shell RCE

CVE-2026-75911
7.8
EPSS 0.3%
Code Execution Supply Chain Agent Plugin
codewhale Patch: 0.8.64 CWE-94 5 ATLAS
HIGH EXPLOIT AVAIL

DeepSeek-TUI: git_blame argument injection leaks files

CVE-2026-75912
7.4
EPSS 0.4%
Prompt Injection Data Leakage Privacy Violation Agent Plugin
codewhale Patch: 0.8.64 CWE-88 4 ATLAS
HIGH EXPLOIT AVAIL

deepseek-tui: SSRF via DNS-pinning TOCTOU bypass

CVE-2026-75856
8.6
EPSS 0.5%
Data Extraction Auth Bypass Agent Plugin
codewhale Patch: 0.8.64 CWE-918 2 ATLAS
HIGH EXPLOIT AVAIL

deepseek-tui: js_execution leaks parent secrets to LLM

CVE-2026-75915
7.5
EPSS 0.6%
Data Leakage Privacy Violation Code Execution Agent Plugin
codewhale Patch: 0.8.64 CWE-200 4 ATLAS
HIGH EXPLOIT AVAIL

CodeWhale: shell approval bypass via interactive tool

CVE-2026-75857
7.0
EPSS 0.2%
Prompt Injection Code Execution Auth Bypass Agent
codewhale Patch: 0.8.64 CWE-269 3 ATLAS
HIGH EXPLOIT AVAIL

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

CVE-2026-85673
7.5
EPSS 0.4%
Auth Bypass Data Extraction API Inference
llama-factory CWE-918 3 ATLAS
HIGH EXPLOIT AVAIL

OGX/Llama Stack: SSRF via MCP tool server_url

CVE-2026-85666
7.5
EPSS 0.4%
Data Leakage Auth Bypass Agent API Plugin
llama-stack CWE-918 13 3 ATLAS
HIGH EXPLOIT AVAIL

SiYuan: WebSocket leak bypasses publish access control

CVE-2026-72810
8.6
EPSS 0.3%
Auth Bypass Data Leakage Privacy Violation Plugin
github.com/siyuan-note/siyuan/kernel Patch: 0.0.0-20260723013612-ba948639d7f6 CWE-862 3.1K 1 ATLAS
HIGH EXPLOIT AVAIL

SiYuan: missing authz leaks forbidden doc content via backlink API

CVE-2026-68586
8.6
EPSS 0.2%
Auth Bypass Data Leakage Privacy Violation API
github.com/siyuan-note/siyuan/kernel Patch: 0.0.0-20260721014413-f45749a7ef6e CWE-862 3.1K 1 ATLAS
HIGH EXPLOIT AVAIL

SiYuan: missing authz exposes publish-disabled docs

CVE-2026-68587
8.6
EPSS 0.2%
Auth Bypass Data Leakage Privacy Violation RAG
github.com/siyuan-note/siyuan/kernel Patch: 0.0.0-20260721013353-69db783b782a CWE-862 3.1K 3 ATLAS
HIGH EXPLOIT AVAIL

Helicone: IDOR leaks cross-tenant LLM provider keys

CVE-2026-85178
7.7
EPSS 0.2%
Auth Bypass Data Leakage API
CWE-639 3 ATLAS
HIGH EXPLOIT AVAIL

Label Studio: org filter bypass leaks tenant storage

CVE-2026-85211
7.7
EPSS 0.2%
Auth Bypass Data Leakage Privacy Violation Training Data API
label-studio 2 3 ATLAS
HIGH EXPLOIT AVAIL

Label Studio: SSRF via webhooks hits cloud metadata

CVE-2026-85179
8.5
EPSS 0.2%
Data Leakage Data Extraction Training Data Framework
label-studio 2 3 ATLAS
HIGH EXPLOIT AVAIL

Codex CLI: git core.fsmonitor hook enables RCE

CVE-2026-19592
7.3
EPSS 0.1%
Code Execution Supply Chain Agent
Codex CLI 1.2K 3 ATLAS
HIGH EXPLOIT AVAIL

SiYuan: stored XSS via malicious bazaar package names

CVE-2026-82653
8.9
EPSS 0.2%
Supply Chain Code Execution Plugin
CWE-79 2 ATLAS
HIGH EXPLOIT AVAIL

NextChat: proxy URL check bypass leaks OpenAI key

CVE-2026-82639
7.5
EPSS 0.3%
Data Leakage Auth Bypass API Framework
CWE-20 3 ATLAS
HIGH EXPLOIT AVAIL

Langflow: authenticated RCE via unsafe code generation

CVE-2026-18729
8.8
EPSS 0.9%
Code Execution Auth Bypass Framework Agent
langflow CWE-94 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