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
2,377

AI/ML CVEs Tracked

337

Critical

392

New This Week

18

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 108 results — Critical severity, has patch
CRITICAL

Budibase: zip symlink bypass exposes all server secrets

CVE-2026-54352
9.6
Data Extraction Auth Bypass Supply Chain Framework API Inference
@budibase/server Patch: 3.39.9 CWE-22 6 7 ATLAS
CRITICAL

Langflow: TAR symlink traversal enables full RCE

CVE-2026-55447
9.6
Code Execution Auth Bypass Data Extraction Framework RAG Agent
langflow Patch: 1.9.2 CWE-61 6 ATLAS
CRITICAL

Langflow: IDOR allows cross-user flow execution

CVE-2026-55255
9.9
Auth Bypass Data Extraction Framework Agent
langflow Patch: 1.9.1 CWE-639 5 ATLAS
CRITICAL

Kirby CMS: admin takeover via reverse proxy header bypass

CVE-2026-54003
--
Auth Bypass Code Execution API Framework
getkirby/cms Patch: 4.9.4 CWE-454 479 3 ATLAS
CRITICAL

praisonai-platform: hardcoded JWT secret enables full auth bypass

GHSA-cwj8-7gp2-ggcw
9.8
Auth Bypass Supply Chain Agent Framework
praisonai-platform Patch: 0.1.6 CWE-798 1 4 ATLAS
CRITICAL

praisonai-platform: hardcoded JWT secret enables full auth bypass

GHSA-f38v-77qj-h4jq
9.8
Auth Bypass Agent Framework
praisonai-platform Patch: 0.1.6 CWE-287 1 5 ATLAS
CRITICAL

PraisonAI: multiedit path traversal, arbitrary file R/W

GHSA-29w3-p9w9-wc47
9.1
Data Extraction Code Execution Privacy Violation Agent Plugin
praisonai Patch: 4.6.61 CWE-22 1 7 ATLAS
CRITICAL

praisonai: MCP HTTP server unauthenticated tool invocation

GHSA-j4f3-55x4-r6q2
9.8
Auth Bypass Code Execution Data Extraction Agent Framework API
praisonai Patch: 1.7.2 CWE-306 1 6 ATLAS
CRITICAL

praisonai npm: AgentOS missing auth enables agent abuse

GHSA-9752-mhqh-h34f
9.4
Auth Bypass Data Extraction Code Execution Agent Framework API
praisonai Patch: 1.7.2 CWE-306 1 6 ATLAS
CRITICAL

praisonai: sandbox escape in codeMode → full host RCE

GHSA-p69m-4f92-2v84
9.8
Code Execution Prompt Injection Data Extraction Agent Framework Plugin
praisonai Patch: 1.7.2 CWE-94 1 6 ATLAS
CRITICAL

praisonai: sandbox escape gives RCE via codeMode tool

GHSA-vmmj-pfw7-fjwp
9.9
Code Execution Supply Chain Prompt Injection Agent Plugin
praisonai Patch: 1.7.2 CWE-184 1 5 ATLAS
CRITICAL

PraisonAI: unauthenticated RCE via MCP connect endpoint

GHSA-p75f-6fp4-p57w
9.8
Code Execution Auth Bypass Agent Framework Plugin
praisonai Patch: 4.6.59 CWE-78 1 5 ATLAS
CRITICAL

PraisonAI AgentOS: unauth remote agent invocation (CVSS 9.8)

GHSA-892r-p3jq-jp24
9.8
Auth Bypass Code Execution Data Extraction Agent Framework API
praisonai Patch: 4.6.59 CWE-200 1 7 ATLAS
CRITICAL

praisonaiagents: unauth AgentTeam API allows agent takeover

GHSA-x8cv-xmq7-p8xp
9.8
Auth Bypass Code Execution DoS Agent Framework
praisonaiagents Patch: 1.6.59 CWE-306 11 5 ATLAS
CRITICAL

praisonai: unauthenticated Jobs API enables remote agent RCE

GHSA-fq2m-6wqh-x44g
9.8
Auth Bypass Code Execution Data Extraction Agent Framework API
praisonai Patch: 4.6.59 CWE-94 1 5 ATLAS
CRITICAL

praisonai: silent auth bypass exposes agent exec endpoints

GHSA-j4hj-7hfh-g2f4
9.8
Auth Bypass Code Execution Agent Framework
praisonai Patch: 4.6.59 CWE-306 1 4 ATLAS
CRITICAL

PraisonAI: Unauthenticated RCE via Jobs API auth bypass

GHSA-4869-x4pr-q22x
9.8
Auth Bypass Code Execution Prompt Injection Agent Framework Plugin
praisonaiagents Patch: 1.6.59 CWE-306 11 5 ATLAS
CRITICAL

praisonaiagents: unauthenticated MCP SSE server enables RCE

GHSA-x227-pf99-vffg
9.8
Auth Bypass Code Execution Agent Framework
praisonaiagents Patch: 1.6.59 CWE-306 11 5 ATLAS
CRITICAL

Langflow: unauthenticated upload → DoS + path disclosure

CVE-2026-55450
9.3
Auth Bypass DoS Data Leakage Framework Agent
langflow Patch: 1.9.1 CWE-400 5 ATLAS
CRITICAL

LiteLLM: auth bypass via Host header spoofing

CVE-2026-49468
--
EPSS 0.1%
Auth Bypass Data Extraction Inference API
litellm Patch: 1.84.0 CWE-290 6 4 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