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
3,628

AI/ML CVEs Tracked

484

Critical

101

New This Week

25

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 1042 results — High severity, no patch
HIGH EXPLOIT AVAIL

Flowise before 3.1.4 fails to scope enterprise organization and workspace membership APIs to the caller's tenant, allowing authenticated users to supply...

CVE-2026-91930
7.5
EPSS 0.4%
CWE-266
HIGH

Flowise versions before 3.1.4 contain cross-tenant authorization gaps in Enterprise endpoints that fail to verify resource ownership before operations....

CVE-2026-91929
7.1
EPSS 0.3%
CWE-862
HIGH EXPLOIT AVAIL

PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to...

CVE-2026-57137
8.8
EPSS 0.4%
CWE-693
HIGH EXPLOIT AVAIL

PraisonAI is a multi-agent teams system. From 1.2.3 until 1.7.2, CommandValidator in src/praisonai-ts/src/cli/features/sandbox-executor.ts validates only the...

CVE-2026-57136
8.8
EPSS 0.4%
CWE-78
HIGH EXPLOIT AVAIL

PraisonAI is a multi-agent teams system. From 1.2.3 until 1.7.2, SandboxExecutor network-isolated mode in src/praisonai-ts/src/cli/features/sandbox-executor.ts...

CVE-2026-57135
7.6
EPSS 0.3%
CWE-653
HIGH EXPLOIT AVAIL

PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, MCPSecurity.evaluatePolicy() in src/praisonai-ts/src/mcp/security.ts invokes the configured...

CVE-2026-57134
8.2
EPSS 0.3%
CWE-287
HIGH EXPLOIT AVAIL

PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, the shell() helper exported from src/praisonai-ts/src/tools/utility-tools.ts checks only the...

CVE-2026-57133
8.8
EPSS 0.4%
CWE-78
HIGH EXPLOIT AVAIL

PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.run_sse() in...

CVE-2026-57112
8.3
EPSS 0.2%
CWE-306
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%
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%
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
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
HIGH

PraisonAI: missing HMAC check lets forged bot events

CVE-2026-57122
8.6
EPSS 0.1%
Auth Bypass Prompt Injection Social Engineering Agent Plugin
praisonai CWE-345 1 4 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: path traversal exposes local files

CVE-2026-57119
7.5
EPSS 0.4%
Data Leakage Privacy Violation Agent Framework
praisonai CWE-22 1 3 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: path traversal escapes agent workspace sandbox

CVE-2026-56839
7.3
EPSS 0.3%
HIGH EXPLOIT AVAIL

PraisonAI: IMAP injection via unsanitized email tool params

CVE-2026-57130
8.1
EPSS 0.3%
Data Leakage Prompt Injection DoS Agent Plugin
praisonaiagents CWE-20 20 4 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: path traversal exposes arbitrary files

CVE-2026-57129
7.5
EPSS 0.4%
Data Leakage Privacy Violation Agent Framework
praisonaiagents CWE-22 20 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