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 1346 results — Active exploitation, no patch
MEDIUMEXPLOIT AVAIL

WPBot: missing auth check leaks chat visitor PII

CVE-2026-87916
5.3
EPSS 0.3%
Auth BypassPrivacy ViolationData LeakageAgentPlugin
WPBot2 ATLAS
CRITICALEXPLOIT AVAIL

Mistral Vibe: env-var trick bypasses command allowlist

CVE-2026-87987
--
EPSS 0.6%
Code ExecutionAuth BypassAgentFramework
mistral-vibe4735 ATLAS
CRITICALEXPLOIT AVAIL

Gemini CLI: RCE via malicious .env GEMINI_CLI_HOME override

CVE-2026-13745
--
EPSS 0.7%
Code ExecutionSupply ChainAgentPlugin
run-gemini-cli GitHub Action4 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: stored XSS in notebook template paths

CVE-2026-87811
7.3
EPSS 0.4%
Code ExecutionData LeakagePlugin
1 ATLAS
UNKNOWNEXPLOIT AVAIL

MLflow: malicious model artifact enables RCE on load

CVE-2026-79721
--
EPSS 0.5%
Supply ChainCode ExecutionFrameworkModel
mlflow6954 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

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
UNKNOWNEXPLOIT AVAIL

csv-parse: CSV header triggers prototype pollution

CVE-2026-85063
--
EPSS 0.6%
Supply ChainAuth BypassTraining DataRAG
CWE-13212 ATLAS
HIGHEXPLOIT AVAIL

Ollama: SSRF via unvalidated model-pull redirects

CVE-2026-85180
7.5
EPSS 0.5%
Supply ChainData LeakageInferenceModel
ollamaCWE-9181.9K4 ATLAS
HIGHEXPLOIT AVAIL

Helicone: IDOR leaks cross-tenant LLM provider keys

CVE-2026-85178
7.7
EPSS 0.4%
Auth BypassData LeakageAPI
CWE-6393 ATLAS
MEDIUMEXPLOIT AVAIL

ckan-mcp-server: cache key collision enables poisoning

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

Label Studio: org filter bypass leaks tenant storage

CVE-2026-85211
7.7
EPSS 0.4%
Auth BypassData LeakagePrivacy ViolationTraining DataAPI
label-studio23 ATLAS
HIGHEXPLOIT AVAIL

Label Studio: SSRF via webhooks hits cloud metadata

CVE-2026-85179
8.5
EPSS 0.4%
Data LeakageData ExtractionTraining DataFramework
label-studio23 ATLAS
HIGHEXPLOIT AVAIL

Craft CMS: auth bypass enables admin takeover

CVE-2026-84801
8.8
EPSS 0.4%
Auth BypassFramework
HIGHEXPLOIT AVAIL

Codex CLI: git core.fsmonitor hook enables RCE

CVE-2026-19592
7.3
EPSS 0.2%
Code ExecutionSupply ChainAgent
Codex CLI1.8K3 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