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 2345 results — no patch
HIGH EXPLOIT AVAIL

InternLM LMDeploy through 0.17.0 in DistServe prefill/decode disaggregation mode fails to release scheduler sessions because the proxy uses user-facing session...

CVE-2026-92983
7.5
EPSS 0.4%
CWE-772
HIGH EXPLOIT AVAIL

InternLM LMDeploy through 0.17.0 contains a reachable assertion vulnerability in the DistServe decode migration loop that allows unauthenticated attackers to...

CVE-2026-92971
7.5
EPSS 0.5%
HIGH

A flaw was found in Redis community. The cluster bus packet parser, responsible for handling PING, PONG, and MEET packets, fails to properly validate...

CVE-2026-92925
7.1
EPSS 0.3%
rhaii/vllm-rocm-rhel9 92
MEDIUM

n8n is a workflow automation platform. In n8n versions before 1.123.76, 2.37.7, and 2.38.2, the source control push endpoint derived the set of files to push...

CVE-2026-92588
4.4
EPSS 0.2%
CWE-639
MEDIUM

n8n is a workflow automation platform. In versions before 1.123.76, 2.37.7, and 2.38.2, the Git node validated a relative remote URL against the configured...

CVE-2026-92587
5.0
EPSS 0.2%
CWE-426
HIGH

LightGBM through 4.7.0 fails to validate child and split array values when parsing text models, allowing attackers to write out-of-bounds memory during SHAP...

CVE-2026-92786
7.8
EPSS 0.1%
CWE-787
HIGH EXPLOIT AVAIL

Pelican Panel versions before 1.0.0-beta35 enforce startup write permissions only through disabled form controls rather than server-side authorization checks....

CVE-2026-92762
8.8
EPSS 0.3%
CWE-862
AWAITING NVD

Kedro-Datasets provides data connectors for Kedro. From version 5.0.0 until 9.5.0, kedro_datasets_experimental.pytorch.PyTorchDataset in kedro-datasets loads...

CVE-2026-62997
--
EPSS 0.4%
CWE-502
MEDIUM

A vulnerability was found in vllm-project vllm up to 0.29.0. Affected by this issue is some unknown functionality of the file...

CVE-2026-92365
4.3
EPSS 0.4%
CWE-404
MEDIUM EXPLOIT AVAIL

The WPBot WordPress plugin before 8.7.6 does not perform a capability check on the AJAX action that saves its Claude AI provider settings, allowing users with...

CVE-2026-87959
5.4
EPSS 0.2%
WPBot
MEDIUM

A vulnerability was found in vllm-project vLLM 0.26.0/0.27.0. Affected is the function...

CVE-2026-92220
5.3
EPSS 0.5%
CWE-400
MEDIUM

EspoCRM through 10.0.8 uses PHP's rand() function to generate tokens for lead-capture opt-in, event invitation, and campaign URLs instead of a...

CVE-2026-92298
4.8
EPSS 0.3%
MEDIUM

Concrete CMS 9.4.0 through 9.5.2 did not escape colliding page paths before rendering them in the location panel's duplicate-path confirmation dialog. The...

CVE-2026-81926
6.1
EPSS 0.4%
HIGH

@zereight/mcp-gitlab has multiple safety-control bypasses: execute_graphql read-only + allow-list bypass, unauthenticated transports, session-exhaustion DoS

GHSA-5648-rgj9-v224
8.1
CWE-863
LOW

Nezha: OAuth2 redirect_uri Host header injection regression when dashboard_host is empty

GHSA-rf68-8gjr-36q7
--
github.com/nezhahq/nezha CWE-601 505
HIGH

Concrete CMS 9 (9.0.0 through 9.5.2) does not perform an authorization check on the user selector autocomplete endpoint (/ccm/system/user/autocomplete), which...

CVE-2026-18110
7.5
EPSS 0.3%
HIGH

Flowise versions before 3.1.4 contain a server-side request forgery vulnerability in Cheerio, Playwright, and Puppeteer document loader nodes that bypass SSRF...

CVE-2026-91938
7.1
EPSS 0.3%
CWE-918
HIGH

Flowise before 3.1.4 fails to sanitize the overrideConfig.sessionId parameter before using it in MongoDB queries within the MongoDBMemory node. Unauthenticated...

CVE-2026-91937
7.5
EPSS 0.3%
CWE-943
MEDIUM EXPLOIT AVAIL

Flowise versions before 3.1.4 contain a script injection vulnerability in Docker image build workflows where workflow_dispatch inputs are directly interpolated...

CVE-2026-91936
6.8
EPSS 0.3%
CWE-78
HIGH EXPLOIT AVAIL

Flowise before 3.1.4 fails to validate baseURL parameters in chat-model nodes, allowing authenticated users to redirect requests to arbitrary hosts. Attackers...

CVE-2026-91935
8.3
EPSS 0.3%
CWE-918

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