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
4,331

AI/ML CVEs Tracked

535

Critical

108

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 4331 results
MEDIUMEXPLOIT AVAIL

PraisonAI: SSRF bypass via loopback alias encodings

CVE-2026-47390
5.5
EPSS 0.2%
Auth BypassData ExtractionAgentPlugin
PraisonAIPatch: 4.6.40CWE-91814 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: RCE via ungated exec_module in agent config

CVE-2026-47398
8.1
EPSS 0.5%
Code ExecutionSupply ChainAgentFramework
PraisonAIPatch: 4.6.40CWE-9415 ATLAS
MEDIUMEXPLOIT AVAIL

BoxLite: sandbox timeout bypass enables DoS via SIGALRM

CVE-2026-47213
6.5
EPSS 0.3%
DoSCode ExecutionAgentInference
boxliteCWE-40454 ATLAS
MEDIUM

PyCharm: stored XSS via Jupyter Markdown cells

CVE-2026-49384
6.1
EPSS 0.2%
Supply ChainData ExtractionCode ExecutionFrameworkAPI
CWE-793 ATLAS
MEDIUM

Shopper: auth bypass enables full checkout shutdown

CVE-2026-47745
6.5
EPSS 0.2%
Auth BypassDoSFramework
shopper/frameworkPatch: 2.8.0CWE-8625143 ATLAS
CRITICAL

Shopper: RBAC bypass allows full admin takeover

CVE-2026-47744
9.9
EPSS 0.3%
Auth BypassCode ExecutionFramework
shopper/frameworkPatch: 2.8.0CWE-2695143 ATLAS
MEDIUM

Shopper: authz bypass lets any user mutate product data

CVE-2026-47742
6.5
EPSS 0.2%
Auth BypassFramework
shopper/frameworkPatch: 2.8.0CWE-8625143 ATLAS
MEDIUM

CAPM3: cross-namespace auth bypass exposes K8s secrets

GHSA-rf84-wr5g-m3rp
5.5
Auth BypassData LeakageFramework
github.com/metal3-io/cluster-api-provider-metal3Patch: 1.11.8CWE-8633 ATLAS
HIGH

OpenClaw: scope bypass enables full agent admin takeover

CVE-2026-35674
8.8
EPSS 0.3%
Auth BypassCode ExecutionSupply ChainAgentPlugin
openclawCWE-86335 ATLAS
MEDIUM

OpenClaw: SSRF bypass exposes private network access

CVE-2026-35673
6.5
EPSS 0.2%
Auth BypassData ExtractionAgent
openclawCWE-86334 ATLAS
HIGH

OpenClaw: auth bypass enables unauthorized agent approval

CVE-2026-35630
8.0
EPSS 0.2%
Auth BypassCode ExecutionAgentPlugin
openclawCWE-86234 ATLAS
MEDIUM

OpenClaw: policy bypass enables unauthorized admin command execution

CVE-2026-34507
5.4
EPSS 0.1%
Auth BypassAgentFramework
openclawCWE-86334 ATLAS
MEDIUM

OpenClaw: privilege escalation bypasses Slack plugin approval gate

CVE-2026-32906
4.3
EPSS 0.2%
Auth BypassCode ExecutionAgentPlugin
openclawCWE-86334 ATLAS
HIGH

OpenClaw: auth bypass enables persistent device enrollment

CVE-2026-32905
8.3
EPSS 0.2%
Auth BypassCode ExecutionAgentPlugin
openclawCWE-86234 ATLAS
HIGHEXPLOIT AVAIL

Froxlor: symlink-following grants customer root SSH access

CVE-2026-41236
8.8
EPSS 0.4%
Auth BypassCode ExecutionInferenceFramework
froxlor/froxlorPatch: 2.3.7CWE-595144 ATLAS
HIGHEXPLOIT AVAIL

Froxlor: shell whitelist bypass grants host shell access

CVE-2026-41235
--
EPSS 0.2%
Auth BypassCode ExecutionAPIInference
froxlor/froxlorPatch: 2.3.7CWE-8635144 ATLAS
MEDIUMEXPLOIT AVAIL

local-deep-research: SSRF via URL parser differential bypass

CVE-2026-46526
5.0
EPSS 0.3%
Auth BypassData ExtractionAgent
local-deep-researchPatch: 1.6.10CWE-9183 ATLAS
UNKNOWNEXPLOIT AVAIL

vllm: trust_remote_code bypass enables RCE via HuggingFace

CVE-2026-4944
--
EPSS 0.7%
Supply ChainCode ExecutionInferenceModel
vllmCWE-22945 ATLAS
MEDIUM

Linux Kernel: DMA coherency bug in xbox_remote driver

CVE-2026-46236
5.5
EPSS 0.1%
Code ExecutionInference
2 ATLAS
HIGH

Linux kernel RDMA/mlx4: RCU race may crash ML training nodes

CVE-2026-46181
7.8
EPSS 0.1%
DoSFramework
1 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