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
4,307

AI/ML CVEs Tracked

533

Critical

96

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 615 results — Active exploitation, has patch
HIGHEXPLOIT AVAIL

PraisonAI: Origin bypass CSRF enables prompt injection

CVE-2026-55532
7.6
EPSS 0.2%
Auth BypassPrompt InjectionAgentPlugin
PraisonAIPatch: 4.6.58CWE-34615 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: auth fail-open lets unauthenticated recipe execution

CVE-2026-55533
8.2
EPSS 0.5%
Auth BypassCode ExecutionAgentAPI
PraisonAIPatch: 4.6.58CWE-28713 ATLAS
UNKNOWNEXPLOIT AVAIL

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

CVE-2026-55541
--
EPSS 0.5%
Auth BypassCode ExecutionAgentAPIFramework
PraisonAIPatch: 4.6.58CWE-86213 ATLAS
MEDIUMEXPLOIT AVAIL

PraisonAI: TOCTOU SSRF in webhook validation

CVE-2026-55535
6.8
EPSS 0.3%
Data LeakageAuth BypassAgentAPI
PraisonAIPatch: 4.6.58CWE-36713 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: SSRF via race condition in webhook DNS check

CVE-2026-55537
7.1
EPSS 0.3%
Code ExecutionData LeakageAgentFramework
PraisonAIPatch: 4.6.58CWE-36712 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: missing auth allows agent execution

CVE-2026-55538
7.3
EPSS 0.4%
Auth BypassCode ExecutionAgentAPI
PraisonAIPatch: 4.6.58CWE-30612 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: symlink escape defeats workspace path checks

CVE-2026-55540
7.1
EPSS 0.4%
Data ExtractionAuth BypassAgentPlugin
PraisonAIPatch: 4.6.58CWE-2213 ATLAS
MEDIUMEXPLOIT AVAIL

PraisonAI: missing authz lets agent mass-rewrite files

CVE-2026-55530
6.1
EPSS 0.2%
Auth BypassCode ExecutionAgentFramework
praisonaiagentsPatch: 1.6.58CWE-862203 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: API key ignored, agent endpoints unauth

CVE-2026-55534
8.6
EPSS 0.5%
Auth BypassDoSAgentAPI
PraisonAIPatch: 4.6.58CWE-30613 ATLAS
MEDIUMEXPLOIT AVAIL

PraisonAI: unauth memory exhaustion via MCP sessions

CVE-2026-55531
6.5
EPSS 0.5%
DoSAgent
PraisonAIPatch: 4.6.58CWE-40012 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: AgentServer auth token never enforced

CVE-2026-55528
8.2
EPSS 0.5%
Auth BypassData LeakageAgentAPI
praisonaiagentsPatch: 1.6.58CWE-306203 ATLAS
MEDIUMEXPLOIT AVAIL

PraisonAI: MCP origin-check bypass runs local tools

CVE-2026-55529
6.9
EPSS 0.2%
Auth BypassCode ExecutionAgentPlugin
PraisonAIPatch: 4.6.58CWE-30614 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: SSRF via redirect bypasses crawl allowlist

CVE-2026-55525
7.5
EPSS 0.5%
Data ExtractionAuth BypassAgentPlugin
praisonaiagentsPatch: 1.6.58CWE-918204 ATLAS
CRITICALEXPLOIT AVAIL

Xinference: eval() on LLM output enables RCE

CVE-2026-61539
10.0
EPSS 1.2%
Code ExecutionPrompt InjectionInferenceAPIAgent
xinferencePatch: 2.7.0CWE-951.8K5 ATLAS
CRITICALEXPLOIT AVAIL

Qinglong panel: unauth admin credential reset bypass

CVE-2026-55445
--
EPSS 0.5%
Auth BypassCode ExecutionFramework
@whyour/qinglongPatch: 2.20.1CWE-2875143 ATLAS
CRITICALEXPLOIT AVAIL

Froxlor: API leaks password hashes & TOTP seeds

CVE-2026-62988
9.0
EPSS 0.6%
Data LeakageAuth BypassAPI
froxlor/froxlorPatch: 2.3.8CWE-200514
CRITICALEXPLOIT AVAIL

CodeWhale: git_show argument injection enables file write

CVE-2026-75913
9.3
EPSS 0.5%
Prompt InjectionCode ExecutionSupply ChainAgent
codewhalePatch: 0.8.64CWE-734 ATLAS
HIGHEXPLOIT AVAIL

CodeWhale: rlm_eval RCE bypasses approval policy

CVE-2026-75858
7.8
EPSS 0.4%
Prompt InjectionCode ExecutionAuth BypassAgentPlugin
codewhalePatch: 0.8.64CWE-945 ATLAS
HIGHEXPLOIT AVAIL

MLflow: missing authz check leaks private artifacts

CVE-2026-69148
7.1
EPSS 0.4%
Auth BypassData LeakageModelAPI
mlflowPatch: 3.15.0CWE-8626953 ATLAS
MEDIUMEXPLOIT AVAIL

MLflow: missing authZ lets users forge dataset lineage

CVE-2026-69146
6.5
EPSS 0.4%
Auth BypassModel PoisoningFrameworkTraining DataAPI
mlflowPatch: 3.15.0CWE-8626952 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