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 497 results — Active exploitation, has patch
CRITICAL EXPLOIT AVAIL

PraisonAI: WebSocket auth bypass hijacks browser agent

CVE-2026-55536
9.1
EPSS 0.3%
Auth Bypass Code Execution Privacy Violation Agent Plugin
PraisonAI Patch: 4.6.58 CWE-284 1 4 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: Origin bypass CSRF enables prompt injection

CVE-2026-55532
7.6
EPSS 0.1%
Auth Bypass Prompt Injection Agent Plugin
PraisonAI Patch: 4.6.58 CWE-346 1 5 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: auth fail-open lets unauthenticated recipe execution

CVE-2026-55533
8.2
EPSS 0.3%
Auth Bypass Code Execution Agent API
PraisonAI Patch: 4.6.58 CWE-287 1 3 ATLAS
UNKNOWN EXPLOIT AVAIL

PraisonAI: no auth on agent serve API (create/invoke)

CVE-2026-55541
--
EPSS 0.3%
Auth Bypass Code Execution Agent API Framework
PraisonAI Patch: 4.6.58 CWE-862 1 3 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: TOCTOU SSRF in webhook validation

CVE-2026-55535
6.8
EPSS 0.2%
Data Leakage Auth Bypass Agent API
PraisonAI Patch: 4.6.58 CWE-367 1 3 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: SSRF via race condition in webhook DNS check

CVE-2026-55537
7.1
EPSS 0.2%
Code Execution Data Leakage Agent Framework
PraisonAI Patch: 4.6.58 CWE-367 1 2 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: missing auth allows agent execution

CVE-2026-55538
7.3
EPSS 0.3%
Auth Bypass Code Execution Agent API
PraisonAI Patch: 4.6.58 CWE-306 1 2 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: symlink escape defeats workspace path checks

CVE-2026-55540
7.1
EPSS 0.3%
Data Extraction Auth Bypass Agent Plugin
PraisonAI Patch: 4.6.58 CWE-22 1 3 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: missing authz lets agent mass-rewrite files

CVE-2026-55530
6.1
EPSS 0.1%
Auth Bypass Code Execution Agent Framework
praisonaiagents Patch: 1.6.58 CWE-862 20 3 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: API key ignored, agent endpoints unauth

CVE-2026-55534
8.6
EPSS 0.3%
Auth Bypass DoS Agent API
PraisonAI Patch: 4.6.58 CWE-306 1 3 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: unauth memory exhaustion via MCP sessions

CVE-2026-55531
6.5
EPSS 0.2%
DoS Agent
PraisonAI Patch: 4.6.58 CWE-400 1 2 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: AgentServer auth token never enforced

CVE-2026-55528
8.2
EPSS 0.3%
Auth Bypass Data Leakage Agent API
praisonaiagents Patch: 1.6.58 CWE-306 20 3 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: MCP origin-check bypass runs local tools

CVE-2026-55529
6.9
EPSS 0.1%
Auth Bypass Code Execution Agent Plugin
PraisonAI Patch: 4.6.58 CWE-306 1 4 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: SSRF via redirect bypasses crawl allowlist

CVE-2026-55525
7.5
EPSS 0.3%
Data Extraction Auth Bypass Agent Plugin
praisonaiagents Patch: 1.6.58 CWE-918 20 4 ATLAS
CRITICAL EXPLOIT AVAIL

Xinference: eval() on LLM output enables RCE

CVE-2026-61539
10.0
EPSS 0.7%
Code Execution Prompt Injection Inference API Agent
xinference Patch: 2.7.0 CWE-95 1.2K 5 ATLAS
CRITICAL EXPLOIT AVAIL

Qinglong panel: unauth admin credential reset bypass

CVE-2026-55445
--
EPSS 0.7%
Auth Bypass Code Execution Framework
@whyour/qinglong Patch: 2.20.1 CWE-287 505 3 ATLAS
CRITICAL EXPLOIT AVAIL

Froxlor: API leaks password hashes & TOTP seeds

CVE-2026-62988
9.0
EPSS 0.7%
Data Leakage Auth Bypass API
froxlor/froxlor Patch: 2.3.8 CWE-200 505
CRITICAL EXPLOIT AVAIL

CodeWhale: git_show argument injection enables file write

CVE-2026-75913
9.3
EPSS 0.3%
Prompt Injection Code Execution Supply Chain Agent
codewhale Patch: 0.8.64 CWE-73 4 ATLAS
HIGH EXPLOIT AVAIL

CodeWhale: rlm_eval RCE bypasses approval policy

CVE-2026-75858
7.8
EPSS 0.3%
Prompt Injection Code Execution Auth Bypass Agent Plugin
codewhale Patch: 0.8.64 CWE-94 5 ATLAS
HIGH EXPLOIT AVAIL

MLflow: missing authz check leaks private artifacts

CVE-2026-69148
7.1
EPSS 0.3%
Auth Bypass Data Leakage Model API
mlflow Patch: 3.15.0 CWE-862 690 3 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