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 1908 results — High severity
HIGHEXPLOIT AVAIL

PraisonAI: shell injection in agent file tools allows RCE

CVE-2026-57117
8.8
EPSS 0.6%
Code ExecutionPrompt InjectionAgentFrameworkPlugin
praisonaiCWE-7814 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: SSRF via webhook DNS rebinding bypass

CVE-2026-57114
7.2
EPSS 0.3%
Auth BypassData LeakageFrameworkAgentAPI
praisonaiCWE-36713 ATLAS
HIGH

PraisonAI: path traversal in template cache deletes dirs

CVE-2026-57113
8.1
EPSS 0.4%
Supply ChainDoSFrameworkAgent
praisonaiCWE-2213 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: stored XSS in approval dashboard forces tool approval

CVE-2026-56840
8.8
EPSS 0.4%
Auth BypassPrompt InjectionCode ExecutionAgentFrameworkPlugin
PraisonAICWE-7914 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: recipe run_stream skips dangerous-tool policy

CVE-2026-56838
7.8
EPSS 0.1%
Code ExecutionSupply ChainAuth BypassAgentFrameworkPlugin
PraisonAICWE-7814 ATLAS
HIGH

PraisonAI: missing webhook auth lets forged Linear events drive agent

CVE-2026-56837
8.6
EPSS 0.2%
Auth BypassPrompt InjectionAgentAPIPlugin
PraisonAICWE-28713 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: unauthenticated recipe server exposes admin

CVE-2026-56836
8.2
EPSS 0.3%
Auth BypassAgentFrameworkAPI
PraisonAICWE-28714 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: Slack app_mention bypasses access policy

CVE-2026-56835
8.3
EPSS 0.2%
Auth BypassData LeakageAgentFrameworkPlugin
PraisonAICWE-86214 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: path traversal in artifact tools leaks files

CVE-2026-56834
7.5
EPSS 0.4%
Data ExtractionData LeakagePrompt InjectionAgentFrameworkPlugin
PraisonAICWE-2216 ATLAS
HIGH

PraisonAI: path traversal exposes agent logs/history

CVE-2026-56833
7.5
EPSS 0.5%
Data ExtractionData LeakageAgentFrameworkPlugin
PraisonAICWE-2214 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: Discord approval bypass allows tool call hijack

CVE-2026-56832
8.8
EPSS 0.1%
Auth BypassCode ExecutionAgentFramework
PraisonAICWE-34513 ATLAS
HIGH

OpenCATS: stored XSS in MRU panel enables admin takeover

CVE-2026-115513
8.7
EPSS 0.3%
Auth BypassData LeakageFramework
CWE-792 ATLAS
HIGH

Flexible GraphRAG: Cypher injection via FalkorDB adapter

CVE-2026-114510
7.1
EPSS 0.4%
Prompt InjectionData ExtractionData LeakageFrameworkRAG
flexible-graphragPatch: 0.8.2CWE-1164 ATLAS
HIGHEXPLOIT AVAIL

virtualenv: shell injection in launcher path runs code

CVE-2026-113722
7.8
EPSS 0.3%
Code ExecutionSupply ChainFramework
virtualenvPatch: 21.14.9CWE-786.3K3 ATLAS
HIGHEXPLOIT AVAIL

nbconvert: path traversal allows arbitrary file write

CVE-2026-114140
--
EPSS 0.5%
Supply ChainCode ExecutionFramework
jupyterCWE-221.9K3 ATLAS
HIGH

Jupyter Server: kernel execute authz bypass via Gateway

CVE-2026-114135
8.8
EPSS 0.5%
Auth BypassCode ExecutionData LeakageFrameworkTraining Data
jupyterCWE-8621.9K4 ATLAS
HIGH

SageMaker SDK: S3 bucket squatting enables RCE

CVE-2026-112408
8.1
EPSS 0.7%
Supply ChainCode ExecutionData LeakageFrameworkTraining DataModel
sagemaker504 ATLAS
HIGH

virtualenv: PS1 escaping flaw allows shell command execution

CVE-2026-113725
7.8
EPSS 0.3%
Code ExecutionSupply ChainFramework
virtualenvPatch: 21.14.7CWE-786.3K3 ATLAS
HIGH

Shopper: missing authorization allows admin escalation

CVE-2026-114387
8.8
EPSS 0.3%
Auth BypassFramework
2 ATLAS
HIGH

vLLM: unvalidated mm_processor_kwargs enables remote DoS

CVE-2026-114055
7.5
EPSS 0.4%
DoSInferenceAPI
vllmPatch: 0.31.0CWE-400943 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