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
MEDIUM EXPLOIT AVAIL

A vulnerability was determined in vllm-project vLLM up to 0.27.1. This affects an unknown part of the file /v1/chat/completions of the component Jinja Template...

CVE-2026-90878
4.3
EPSS 0.3%
CWE-400
HIGH

Weights & Biases wandb before 0.29.0 fails to validate the file name from server responses in the File.download function, allowing path traversal attacks....

CVE-2026-91771
8.8
EPSS 0.7%
CWE-22
HIGH EXPLOIT AVAIL

Incorrect privilege assignment in the admin user-management component of Webkul Bagisto 2.4.9 allows an authenticated backend user holding only the...

CVE-2026-79411
8.8
EPSS 0.3%
AWAITING NVD

Concrete CMS 9.0.0 through 9.5.3 is vulnerable to stored XSS via the custom page alias name (customAliasName) because the Edit Alias dialog applied only trim()...

CVE-2026-18117
--
EPSS 0.3%
CRITICAL

IBM Langflow OSS 1.0.0 through 1.10.0 can allow attackers to execute arbitrary Python code with root privileges (UID=0) on the Langflow server by submitting...

CVE-2026-12944
9.6
EPSS 0.2%
CWE-918
MEDIUM EXPLOIT AVAIL

A security flaw has been discovered in netease-youdao LobsterAI 2026.6.15/2026.8.28/2026.9.3/2026.9.4. Impacted is the function...

CVE-2026-90818
4.3
EPSS 0.5%
CWE-918
HIGH

Concrete CMS 9 through 9.5.2 did not validate a CSRF token in the orphaned block removal panel action (removeOrphanedBlocks). A remote attacker could craft a...

CVE-2026-81902
8.1
EPSS 0.2%
MEDIUM

IBM Cognos Analytics 12.1.0 through 12.1.3 FP1, and 12.0.4 through 12.0.4 FP2 allows a non-privileged user to edit their given name and surname to include...

CVE-2026-7884
5.4
EPSS 0.2%
CWE-79
MEDIUM

IBM Langflow OSS 1.0.0 through 1.11.5 is vulnerable to server-side request forgery (SSRF). This may allow an unauthenticated attacker to send unauthorized...

CVE-2026-12767
6.5
EPSS 0.2%
CWE-918
MEDIUM

IBM Langflow OSS 1.0.0 through 1.11.2 is vulnerable to server-side request forgery (SSRF). This may allow an authenticated attacker to send unauthorized...

CVE-2026-12766
5.4
EPSS 0.2%
CWE-918
MEDIUM

IBM Langflow OSS 1.0.0 through 1.10.2 is vulnerable to server-side request forgery (SSRF). This may allow an unauthenticated attacker to send unauthorized...

CVE-2026-12765
6.5
EPSS 0.2%
CWE-918
MEDIUM

IBM Langflow OSS 1.0.0 through 1.11.5 could allow an authenticated attacker to access another user's MCP server context due to improper cache key isolation in...

CVE-2026-12763
4.2
EPSS 0.1%
CWE-306
MEDIUM EXPLOIT AVAIL

Tract is a tiny, no-nonsense, self-contained TensorFlow and ONNX inference toolkit. Prior to 0.21.16, 0.22.2, and 0.23.1, tract-nnef uses unchecked usize...

CVE-2026-55093
6.1
EPSS 0.2%
CWE-125
MEDIUM

IBM Langflow OSS 1.0.0 through 1.10.2 could allow a remote authenticated attacker to change the password of an account due to improper authentication.

CVE-2026-17628
5.4
EPSS 0.3%
MEDIUM

MCP Atlassian is a Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). From 0.17.0 until 0.22.0, validate_url_for_ssrf resolves...

CVE-2026-73497
6.5
EPSS 0.2%
mcp-atlassian 1
HIGH EXPLOIT AVAIL

MCP Atlassian is a Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Prior to 0.22.0, the confluence_upload_attachment and...

CVE-2026-73496
7.7
EPSS 0.3%
mcp-atlassian 1
HIGH

dd-trace-java: baggage header parsing causes DoS

CVE-2026-50270
7.5
EPSS 0.6%
DoS API
CWE-770 2 ATLAS
HIGH

Filament Comments: stored XSS via admin panel

CVE-2026-90943
8.7
EPSS 0.2%
Auth Bypass Data Leakage Framework Plugin
CWE-79 1 ATLAS
CRITICAL

PraisonAI: path traversal lets agents read/write any file

CVE-2026-57145
9.1
EPSS 0.4%
Prompt Injection Data Leakage Code Execution Agent Plugin
praisonai CWE-22 1 4 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: auth bypass on agent invoke endpoint

CVE-2026-57132
8.2
EPSS 0.3%
Auth Bypass Data Leakage Agent API
praisonai CWE-287 1 4 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