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 1346 results — Active exploitation, no patch
CRITICALEXPLOIT AVAIL

PraisonAI: hardcoded JWT secret enables auth bypass

CVE-2026-57148
9.8
EPSS 0.6%
Auth BypassFrameworkAgentAPI
praisonaiCWE-28713 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: hardcoded JWT secret allows auth bypass

CVE-2026-57147
9.8
EPSS 0.8%
Auth BypassAgentAPIFramework
praisonaiCWE-79813 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: codeMode sandbox escape allows unauthenticated RCE

CVE-2026-57141
9.8
EPSS 0.7%
Code ExecutionPrompt InjectionAgentFrameworkPlugin
praisonaiCWE-9416 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: unauthenticated AgentOS API exposes agents

CVE-2026-57140
9.4
EPSS 0.6%
Auth BypassData LeakageAgentAPIFramework
praisonaiCWE-30615 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: unauthenticated MCP server exposes agent tools

CVE-2026-57139
9.8
EPSS 0.8%
Auth BypassData ExtractionCode ExecutionAgentPluginFramework
praisonaiCWE-30615 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: codeMode sandbox escape allows RCE

CVE-2026-57138
9.9
EPSS 0.7%
Code ExecutionData LeakageAgentFrameworkPlugin
praisonaiCWE-18415 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: approval bypass runs rejected agent tools

CVE-2026-57137
8.8
EPSS 0.5%
Auth BypassCode ExecutionAgentFramework
praisonaiCWE-69313 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: command injection bypasses sandbox allowlist

CVE-2026-57136
8.8
EPSS 0.5%
Code ExecutionAuth BypassAgentFrameworkPlugin
praisonaiCWE-7813 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: sandbox network isolation bypass via proxy env

CVE-2026-57135
7.6
EPSS 0.4%
Data LeakageCode ExecutionAgentFramework
praisonaiCWE-65314 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: MCP auth bypass via unchecked Basic/OAuth

CVE-2026-57134
8.2
EPSS 0.4%
Auth BypassData LeakageAgentFrameworkPlugin
praisonaiCWE-28714 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: allowlist bypass in shell() enables RCE

CVE-2026-57133
8.8
EPSS 0.8%
Code ExecutionPrompt InjectionAgentFrameworkPlugin
praisonaiCWE-7814 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: DNS rebinding exposes MCP SSE tool calls

CVE-2026-57112
8.3
EPSS 0.2%
Auth BypassCode ExecutionData LeakageAgentFrameworkPlugin
praisonaiagentsCWE-306204 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: chat_template abuse causes resource exhaustion

CVE-2026-90878
4.3
EPSS 0.5%
DoSInferenceAPI
vllmCWE-400943 ATLAS
HIGHEXPLOIT AVAIL

Bagisto: privilege escalation to full admin via role change

CVE-2026-79411
8.8
EPSS 0.5%
Auth BypassData LeakageFramework
2 ATLAS
MEDIUMEXPLOIT AVAIL

LobsterAI: SSRF in browser network config sync

CVE-2026-90818
4.3
EPSS 0.5%
Data LeakageAgentFramework
CWE-9182 ATLAS
MEDIUMEXPLOIT AVAIL

tract-nnef: integer overflow enables heap OOB read, crash

CVE-2026-55093
6.1
EPSS 0.2%
DoSData LeakageSupply ChainInferenceFrameworkModel
CWE-1253 ATLAS
MEDIUMEXPLOIT AVAIL

MCP Atlassian: DNS rebinding SSRF reaches cloud metadata

CVE-2026-73497
6.5
EPSS 0.4%
Data LeakageData ExtractionAgentPluginAPI
mcp-atlassian23 ATLAS
HIGHEXPLOIT AVAIL

MCP Atlassian: path traversal enables server file disclosure

CVE-2026-73496
7.7
EPSS 0.5%
Data ExtractionData LeakageAgentPlugin
mcp-atlassian25 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: auth bypass on agent invoke endpoint

CVE-2026-57132
8.2
EPSS 0.5%
Auth BypassData LeakageAgentAPI
praisonaiCWE-28714 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: no-auth API exposes agent execution

CVE-2026-57131
9.8
EPSS 1.0%
Auth BypassCode ExecutionData LeakageFrameworkAgentAPI
praisonai16 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