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 4307 results
HIGH

Filament: recovery codes bypass app-based MFA

CVE-2026-77567
8.1
EPSS 0.6%
Auth BypassFramework
CWE-287
HIGHEXPLOIT AVAIL

Label Studio: IDOR exposes cross-org annotations

CVE-2026-76073
8.8
EPSS 0.5%
Auth BypassData LeakageModel PoisoningTraining DataAPI
label-studio24 ATLAS
CRITICAL

DrayTek VigorAP: pre-auth UDP command injection to root

CVE-2026-71914
9.8
EPSS 2.6%
Code ExecutionPlugin
HIGHEXPLOIT AVAIL

Xinference: RCE via forced trust_remote_code=True

CVE-2026-76841
8.8
EPSS 1.0%
Code ExecutionSupply ChainInferenceModelFramework
CWE-944 ATLAS
HIGH

RPM rpmbuild: macro injection allows code execution

CVE-2026-78367
7.0
Code ExecutionSupply ChainFramework
rhoai/odh-mlflow-operator-rhel96953 ATLAS
MEDIUM

adm-zip: arbitrary file overwrite via symlink extraction

CVE-2026-76845
6.5
EPSS 0.2%
Code ExecutionSupply ChainFrameworkAgent
adm-zipCWE-5921 ATLAS
HIGH

Velociraptor: NOTEBOOK_EDIT users can overwrite artifacts

CVE-2026-19200
8.9
EPSS 0.3%
Auth BypassCode ExecutionFrameworkPlugin
2 ATLAS
MEDIUMEXPLOIT AVAIL

BentoML: SSRF via unfiltered CGNAT range

CVE-2026-78205
5.8
EPSS 0.4%
Data LeakageAuth BypassInferenceFramework
bentomlCWE-918232 ATLAS
MEDIUMEXPLOIT AVAIL

FiboSearch: unauthenticated AJAX leaks password-protected products

CVE-2026-16612
5.3
EPSS 0.3%
Auth BypassData LeakagePrivacy ViolationPlugin
MEDIUM

Picotls: unbounded ASN.1 recursion crashes on malicious key

CVE-2026-45271
5.5
EPSS 0.2%
DoSAPIInference
picotls271 ATLAS
CRITICALEXPLOIT AVAIL

Xinference: eval() on LLM output enables RCE

CVE-2026-61539
10.0
EPSS 1.2%
Code ExecutionPrompt InjectionInferenceAPIAgent
xinferencePatch: 2.7.0CWE-951.8K5 ATLAS
HIGHEXPLOIT AVAIL

ONNX: TOCTOU symlink bug allows arbitrary file overwrite

CVE-2026-49114
7.1
EPSS 0.2%
Code ExecutionSupply ChainModelFramework
onnx1.1K3 ATLAS
CRITICAL

Headroom LLM proxy: IDOR exposes cross-user memory

CVE-2026-77776
9.1
EPSS 0.6%
Auth BypassData LeakagePrivacy ViolationAPIAgent
3 ATLAS
HIGH

Headroom: SSRF via client-set upstream base URL

CVE-2026-77775
8.6
EPSS 0.6%
Data LeakageAuth BypassPrivacy ViolationAPIInference
2 ATLAS
HIGH

Rocket.Chat: unauth stored HTML injection baits Livechat agents

CVE-2026-65644
7.5
EPSS 0.5%
Social EngineeringCode ExecutionAPI
2 ATLAS
HIGHEXPLOIT AVAIL

LangChain: SitemapLoader SSRF bypasses domain restriction

CVE-2026-72848
8.6
EPSS 0.6%
Data LeakageData ExtractionFrameworkRAG
langchain-communityCWE-9181.3K3 ATLAS
CRITICALEXPLOIT AVAIL

Qinglong panel: unauth admin credential reset bypass

CVE-2026-55445
--
EPSS 0.5%
Auth BypassCode ExecutionFramework
@whyour/qinglongPatch: 2.20.1CWE-2875143 ATLAS
LOW

Coder: stored HTML injection via appearance settings (Owner-only)

GHSA-h58c-xccx-75m3
3.4
Social EngineeringCode ExecutionAgent
github.com/coder/coder/v2Patch: 2.34.2CWE-746.3K1 ATLAS
LOW

Coder: account enumeration via password hash flaw

GHSA-8fxq-53rx-ph5f
3.7
Privacy ViolationSocial EngineeringAPI
github.com/coder/coder/v2Patch: 2.34.2CWE-2036.3K1 ATLAS
HIGH

LangGraph Mongo: NoSQL injection exposes tenant data

CVE-2026-55253
7.7
EPSS 0.5%
Auth BypassData LeakageFrameworkAgent
langgraph-store-mongodbPatch: 0.4.0CWE-9434.1K3 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