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 2876 results — no patchCVE-2025-29770vLLM: DoS via unbounded grammar cache exhausts disk6.50.5%vllmMar 19CRITECVE-2025-1550Keras: safe_mode bypass enables RCE via model loading9.82.6%kerasMar 11LOWECVE-2025-2149PyTorch: improper init in quantized sigmoid skews model output2.50.3%torchMar 10HIGHECVE-2025-2148PyTorch: memory corruption in JIT profiler callback handler7.50.4%torchMar 10CRITECVE-2025-1945picklescan: ZIP flag bypass enables RCE in PyTorch models9.80.6%picklescanMar 10CRITCVE-2024-13147B2B Login Panel: SQLi enables unauthenticated DB access9.80.4%B2B Login PanelMar 5LOWCVE-2025-1953vLLM AIBrix: weak hash in prefix cache leaks inference patterns2.60.3%—Mar 4HIGHECVE-2025-25185gpt_academic: symlink traversal exposes all server files7.50.6%gpt_academicMar 3CRITCVE-2024-13152Mobuy Panel: SQLi allows unauthenticated DB takeover10.00.5%Mobuy Online Machinery Monitoring PanelFeb 14CRITCVE-2024-12366PandasAI: prompt injection enables unauthenticated RCE9.81.2%—Feb 11MEDIECVE-2024-11831serialize-javascript: XSS via regex in AI/ML dashboards5.41.1%odh-kf-notebook-controller-rhel8Feb 10LOWCVE-2025-25183vLLM: hash collision enables prefix cache poisoning2.60.2%vllmFeb 7HIGHCVE-2025-24357vLLM: unsafe deserialization RCE via model loading8.80.9%vllmJan 27MEDICVE-2024-13698Jobify WP: missing authz allows OpenAI key abuse, SSRF6.50.3%—Jan 24HIGHCVE-2025-23205nbgrader: Clickjacking exposes formgrader via IFrame—0.5%—Jan 17HIGHECVE-2025-23042Gradio: ACL bypass via path case manipulation7.51.0%gradioJan 14MEDIECVE-2024-55459Keras: path traversal enables arbitrary file write6.50.2%kerasJan 8UNKNCVE-2025-21604AIDeepin: MD5 collision enables RAG knowledge base poisoning—0.3%—Jan 6UNKNCVE-2024-56516free-one-api: MD5 hashing allows credential cracking—0.3%—Dec 30MEDIECVE-2024-11896WP Text Prompter: Stored XSS in OpenAI shortcode plugin6.40.3%—Dec 24Frequently 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