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 1295 results — High severity, no patchpicklescan: detection bypass enables RCE via pickle files
CVE-2025-71378picklescan: detection bypass enables RCE via malicious models
CVE-2025-71357picklescan: scanner bypass enables RCE via pickle files
CVE-2025-71351picklescan: scanner bypass enables supply chain RCE
CVE-2025-71348litellm: auth bypass in SSO debug exposes LLM proxy
CVE-2026-12795litellm: JWT auth bypass in M2M proxy handler
CVE-2026-12771litellm: auth bypass in Admin Key Handler endpoint
CVE-2026-12770vLLM: sparse tensor DoS/memory corruption via embeddings
CVE-2026-56340vLLM: ReDoS via crafted API input causes DoS
CVE-2025-71379mcp-searxng: SSRF via DNS rebinding in web_url_read
GHSA-mrvx-jmjw-vggcmcp-searxng: DoS via unbounded URL response read
GHSA-xcqx-9jf5-w339Stanza: pickle fallback bypass enables model RCE
CVE-2026-54499libaom: AV1 SVC OOB write enables RCE
CVE-2026-56211libaom: AV1 SVC bounds-check miss leaks heap, crashes
CVE-2026-56210libaom: heap overflow in AV1 encoder LAP mode
CVE-2026-56208libaom: arbitrary address write in AV1 SVC codec
CVE-2026-56209agentic-flow: MCP tool args enable OS command injection RCE
GHSA-vcv2-r9jh-99m5PraisonAI: path traversal → arbitrary file read/write/RCE
CVE-2026-56078PraisonAI: CORS bypass enables arbitrary agent execution
CVE-2026-56076PraisonAI: RCE via hardcoded approval_mode bypass
CVE-2026-56075Frequently 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