Nothing is stored. No sign-up.
Next steps
One useful email every Monday
New free tools, AI and network threats that matter, and one quick challenge. No spam, unsubscribe in one click.
How to use it
- 1
Filter by severity, ecosystem or package.
- 2
Check whether your version is in the vulnerable range.
- 3
Upgrade to the patched version.
Questions people ask
Where does the data come from?
The GitHub Advisory Database (reviewed advisories, CC-BY 4.0), refreshed every 6 hours.
Which packages are covered?
More than 50 popular AI packages, including LangChain, LlamaIndex, Transformers, PyTorch, vLLM, Gradio, MLflow, Ray, LiteLLM, the OpenAI and Anthropic SDKs, MCP SDKs, n8n, Flowise, Ollama and LocalAI.
Is a package missing?
The list is shown on the page. Use the AI package checker to look up any other PyPI or npm package.
Related tools
- Weekly AI threat briefThis week’s AI vulnerabilities in one page, with what to patch first.
- AI package & model checkerIs this pip, npm or Hugging Face name real and safe? Slopsquatting, CVEs and pickle files.
- Malicious AI packagesFake OpenAI, Claude and LangChain packages caught as malware on npm and PyPI.
- Deepfake & AI scam checkIs that voice or video call real? Red flags and how to verify before you pay.
- AI crawler IP checkIs this IP really GPTBot, ClaudeBot or Googlebot? Plus a robots.txt builder for AI bots.
Link to this tool
Found it useful? Paste this into your blog, wiki or runbook.
<a href="https://toolbini.com/ioc/ai-vulnerabilities/">AI vulnerability feed</a>Reviewed by the editorial team · Last reviewed 2026-11 · Report an error