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
2,390

AI/ML CVEs Tracked

342

Critical

304

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 826 results — has patch
MEDIUM

praisonai-platform: IDOR exposes cross-tenant activity logs

CVE-2026-47408
6.5
EPSS 0.0%
Auth Bypass Data Extraction Privacy Violation Agent API
praisonai-platform Patch: 0.1.4 CWE-639 1 3 ATLAS
HIGH

praisonai-platform: IDOR allows full workspace takeover

CVE-2026-48169
8.8
EPSS 0.0%
Auth Bypass Data Extraction Privacy Violation Agent Framework API
praisonai-platform Patch: 0.1.4 CWE-639 1 5 ATLAS
HIGH

PraisonAI: arbitrary file write via hidden webpage metadata

CVE-2026-47397
--
EPSS 0.1%
Prompt Injection Code Execution Agent Plugin
PraisonAI Patch: 4.6.40 CWE-22 1 5 ATLAS
CRITICAL

PraisonAI: Unauth RCE via A2A eval injection

CVE-2026-47391
9.8
EPSS 0.1%
Code Execution Auth Bypass Prompt Injection Agent Framework Plugin
PraisonAI Patch: 4.6.40 CWE-95 1 6 ATLAS
HIGH

PraisonAI: MCP path traversal exfiltrates host credentials

CVE-2026-47394
--
EPSS 0.1%
Data Extraction Auth Bypass Data Leakage Agent Plugin Framework
PraisonAI Patch: 4.6.40 CWE-22 1 6 ATLAS
CRITICAL

praisonaiagents: RCE via Python sandbox bypass

CVE-2026-47392
9.9
EPSS 0.1%
Code Execution Auth Bypass Agent Framework
PraisonAI Patch: 4.6.40 CWE-184 1 6 ATLAS
MEDIUM

PraisonAI: SSRF via @url mention exposes localhost services

CVE-2026-47395
5.5
EPSS 0.0%
Prompt Injection Data Extraction Data Leakage Agent Framework
PraisonAI Patch: 4.6.40 CWE-200 1 5 ATLAS
CRITICAL

PraisonAI: auth bypass in deployed API exposes LLM + tools

CVE-2026-47393
9.8
EPSS 0.1%
Auth Bypass Code Execution Data Leakage Agent Framework API
PraisonAI Patch: 4.6.40 CWE-306 1 7 ATLAS
CRITICAL

PraisonAI: fail-open auth exposes remote agent control API

CVE-2026-47396
9.8
EPSS 0.1%
Auth Bypass Code Execution Data Extraction Agent API Framework
PraisonAI Patch: 4.6.40 CWE-284 1 6 ATLAS
MEDIUM

PraisonAI: SSRF bypass via loopback alias encodings

CVE-2026-47390
5.5
EPSS 0.0%
Auth Bypass Data Extraction Agent Plugin
PraisonAI Patch: 4.6.40 CWE-918 1 4 ATLAS
HIGH

PraisonAI: RCE via ungated exec_module in agent config

CVE-2026-47398
8.1
EPSS 0.1%
Code Execution Supply Chain Agent Framework
PraisonAI Patch: 4.6.40 CWE-94 1 5 ATLAS
MEDIUM

Shopper: auth bypass enables full checkout shutdown

CVE-2026-47745
6.5
EPSS 0.2%
Auth Bypass DoS Framework
shopper/framework Patch: 2.8.0 CWE-862 479 3 ATLAS
CRITICAL

Shopper: RBAC bypass allows full admin takeover

CVE-2026-47744
9.9
EPSS 0.3%
Auth Bypass Code Execution Framework
shopper/framework Patch: 2.8.0 CWE-269 479 3 ATLAS
MEDIUM

Shopper: authz bypass lets any user mutate product data

CVE-2026-47742
6.5
EPSS 0.2%
Auth Bypass Framework
shopper/framework Patch: 2.8.0 CWE-862 479 3 ATLAS
MEDIUM

CAPM3: cross-namespace auth bypass exposes K8s secrets

GHSA-rf84-wr5g-m3rp
5.5
Auth Bypass Data Leakage Framework
github.com/metal3-io/cluster-api-provider-metal3 Patch: 1.11.8 CWE-863 3 ATLAS
HIGH EXPLOIT AVAIL

Froxlor: symlink-following grants customer root SSH access

CVE-2026-41236
8.8
EPSS 0.4%
Auth Bypass Code Execution Inference Framework
froxlor/froxlor Patch: 2.3.7 CWE-59 479 4 ATLAS
HIGH EXPLOIT AVAIL

Froxlor: shell whitelist bypass grants host shell access

CVE-2026-41235
--
EPSS 0.2%
Auth Bypass Code Execution API Inference
froxlor/froxlor Patch: 2.3.7 CWE-863 479 4 ATLAS
MEDIUM

nono-cli: sandbox escape via Unix socket bypass

CVE-2026-47128
6.1
EPSS 0.0%
Code Execution Auth Bypass Agent Plugin
nono-cli Patch: 0.55.0 CWE-863 4 ATLAS
MEDIUM EXPLOIT AVAIL

local-deep-research: SSRF via URL parser differential bypass

CVE-2026-46526
5.0
EPSS 0.2%
Auth Bypass Data Extraction Agent
local-deep-research Patch: 1.6.10 CWE-918 3 ATLAS
CRITICAL EXPLOIT AVAIL

langroid: Prompt-to-SQL injection enables RCE on DB host

CVE-2026-25879
9.8
EPSS 0.4%
Prompt Injection Code Execution Data Extraction Agent Framework
langroid Patch: 0.63.0 CWE-89 4 6 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