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.
- 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 1566 results — no patch CVE-2025-29770 vLLM: DoS via unbounded grammar cache exhausts disk 6.5 0.4% vllm Mar 19 CRIT E CVE-2025-1550 Keras: safe_mode bypass enables RCE via model loading 9.8 2.8% keras Mar 11 LOW E CVE-2025-2149 PyTorch: improper init in quantized sigmoid skews model output 2.5 0.2% torch Mar 10 HIGH E CVE-2025-2148 PyTorch: memory corruption in JIT profiler callback handler 7.5 0.4% torch Mar 10 CRIT E CVE-2025-1945 picklescan: ZIP flag bypass enables RCE in PyTorch models 9.8 0.5% picklescan Mar 10 CRIT CVE-2024-13147 B2B Login Panel: SQLi enables unauthenticated DB access 9.8 0.4% B2B Login Panel Mar 5 LOW CVE-2025-1953 vLLM AIBrix: weak hash in prefix cache leaks inference patterns 2.6 0.3% — Mar 4 HIGH E CVE-2025-25185 gpt_academic: symlink traversal exposes all server files 7.5 0.6% gpt_academic Mar 3 CRIT CVE-2024-13152 Mobuy Panel: SQLi allows unauthenticated DB takeover 10.0 0.5% Mobuy Online Machinery Monitoring Panel Feb 14 CRIT CVE-2024-12366 PandasAI: prompt injection enables unauthenticated RCE 9.8 1.2% — Feb 11 MEDI CVE-2024-11831 serialize-javascript: XSS via regex in AI/ML dashboards 5.4 1.0% odh-kf-notebook-controller-rhel8 Feb 10 LOW CVE-2025-25183 vLLM: hash collision enables prefix cache poisoning 2.6 0.2% vllm Feb 7 HIGH CVE-2025-24357 vLLM: unsafe deserialization RCE via model loading 8.8 0.6% vllm Jan 27 MEDI CVE-2024-13698 Jobify WP: missing authz allows OpenAI key abuse, SSRF 6.5 0.3% — Jan 24 HIGH CVE-2025-23205 nbgrader: Clickjacking exposes formgrader via IFrame — 0.5% — Jan 17 HIGH E CVE-2025-23042 Gradio: ACL bypass via path case manipulation 7.5 0.8% gradio Jan 14 MEDI E CVE-2024-55459 Keras: path traversal enables arbitrary file write 6.5 0.2% keras Jan 8 UNKN CVE-2025-21604 AIDeepin: MD5 collision enables RAG knowledge base poisoning — 0.2% — Jan 6 UNKN CVE-2024-56516 free-one-api: MD5 hashing allows credential cracking — 0.3% — Dec 30 MEDI E CVE-2024-11896 WP Text Prompter: Stored XSS in OpenAI shortcode plugin 6.4 0.3% — Dec 24 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