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 1431 results — has patch
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
HIGH

PraisonAI: SSRF bypass via DNS-rebinding hostname

CVE-2026-55526
8.5
EPSS 0.4%
Auth BypassData ExtractionAgentPlugin
praisonaiagentsPatch: 1.6.58CWE-350203 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
LOW

Coder: stored HTML injection via appearance settings (Owner-only)

GHSA-h58c-xccx-75m3
3.4
Social EngineeringCode ExecutionAgent
github.com/coder/coder/v2Patch: 2.34.2CWE-746.3K1 ATLAS
LOW

Coder: account enumeration via password hash flaw

GHSA-8fxq-53rx-ph5f
3.7
Privacy ViolationSocial EngineeringAPI
github.com/coder/coder/v2Patch: 2.34.2CWE-2036.3K1 ATLAS
HIGH

LangGraph Mongo: NoSQL injection exposes tenant data

CVE-2026-55253
7.7
EPSS 0.5%
Auth BypassData LeakageFrameworkAgent
langgraph-store-mongodbPatch: 0.4.0CWE-9434.1K3 ATLAS
HIGH

GeoLens: authz flaws leak private geospatial data

GHSA-p77j-g7h5-r2vw
--
Auth BypassData LeakagePrivacy ViolationTraining DataAPIRAG
geolensPatch: 1.2.4CWE-932.8K4 ATLAS
MEDIUM

LangGraph API: authz bypass leaks assistant config

CVE-2026-55236
5.9
EPSS 0.3%
Auth BypassData LeakageFrameworkAgentAPI
langgraph-apiPatch: 0.10.0CWE-2854.1K2 ATLAS
MEDIUM

langgraph-api: loopback webhook bypasses cross-user auth

CVE-2026-55235
5.9
EPSS 0.4%
Auth BypassPrivacy ViolationFrameworkAgentAPI
langgraph-apiPatch: 0.10.0CWE-2874.1K1 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
HIGH

Froxlor: stored XSS in DNS TXT record hijacks admin

CVE-2026-54347
8.7
EPSS 0.4%
Code ExecutionPrivacy ViolationFramework
froxlor/froxlorPatch: 2.3.8CWE-79514
HIGH

MONAI: NumpyReader RCE via forced allow_pickle=True

GHSA-wg9g-w2j2-8pgr
7.8
Supply ChainCode ExecutionFrameworkTraining Data
monaiPatch: 1.6.0CWE-5021284 ATLAS
HIGH

MONAI: OS command injection via crafted YAML config

GHSA-rghg-q7wp-9767
--
Code ExecutionSupply ChainFrameworkTraining Data
MONAIPatch: 1.6.0CWE-781284 ATLAS
HIGH

MONAI: unpatched pickle deserialization enables RCE

GHSA-qxq5-qhx6-94qw
7.8
Code ExecutionSupply ChainFrameworkTraining Data
monaiPatch: 1.6.0CWE-5021283 ATLAS
HIGH

MeshCentral: stored XSS via unsanitized agent osdesc field

GHSA-c7hr-448w-65px
8.3
Code ExecutionPrivacy ViolationAgent
meshcentralPatch: 1.1.60CWE-20514

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