AI Threat AlertAI 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.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 1961 results — Active exploitationCVE-2026-41265Flowise: RCE via prompt injection in Airtable Agent9.80.6%flowiseApr 23HIGHECVE-2026-41138Flowise: RCE via unsanitized input in AirtableAgent8.80.6%flowiseApr 23HIGHECVE-2026-41137Flowise: RCE via CSVAgent unsanitized code injection8.81.5%flowiseApr 23CRITECVE-2026-41264Flowise: prompt injection → unsandboxed RCE via CSV Agent9.81.8%flowise-componentsApr 21MEDIECVE-2026-6608FastChat: control flow flaw corrupts arena comparison5.30.3%fschatApr 20LOWECVE-2026-6600Langflow: stored XSS in chat message editor3.50.2%langflowApr 20MEDIECVE-2026-6599Langflow: MCP config injection via X-Forwarded-For header6.30.2%langflowApr 20MEDIECVE-2026-6598Langflow: cleartext auth storage exposes API keys4.30.2%langflowApr 20LOWECVE-2026-6597langflow: Plaintext credential storage via Flow API2.70.4%langflowApr 20HIGHECVE-2026-6596Langflow: unauthenticated file upload allows RCE7.30.3%langflow-baseApr 20CRITECVE-2026-40933Flowise: RCE via MCP stdio command injection9.912.0%flowise-componentsApr 16CRITECVE-2025-61260OpenAI Codex CLI: RCE via malicious MCP config files9.86.7%@openai/codexApr 14HIGHECVE-2026-1462Keras: safe_mode bypass allows RCE via model deserialization8.80.4%kerasApr 13MEDIECVE-2026-40190langsmith: prototype pollution enables auth bypass, RCE5.60.3%langsmithApr 10MEDIECVE-2026-40086rembg: path traversal exposes arbitrary files via HTTP API5.30.6%rembgApr 10HIGHECVE-2026-40114PraisonAI: unauthenticated SSRF via unvalidated webhook_url7.20.2%PraisonAIApr 10HIGHECVE-2026-40160praisonaiagents: SSRF in web_crawl exposes cloud metadata—0.5%praisonaiagentsApr 10MEDIECVE-2026-40159PraisonAI: MCP env inheritance exposes API keys5.50.2%PraisonAIApr 10CRITECVE-2026-40157PraisonAI: path traversal allows arbitrary file write via recipe unpack—0.4%PraisonAIApr 10HIGHECVE-2026-40156PraisonAI: auto tools.py load enables local RCE7.80.2%praisonaiApr 10Frequently 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