The Anti-Virus for AI Artifacts & RAG Firewall. A static analysis tool scanning Models and Notebooks for RCE, Datasets and RAG docs for Data Poisoning, PII, and Prompt Injections. Secure your AI Supply Chain.
Veritensor is the Anti-Virus for AI Artifacts and the ultimate Firewall for RAG pipelines. It secures the entire AI Supply Chain by scanning the artifacts that traditional SAST tools miss: Models, Datasets, RAG Documents, and Notebooks.
Veritensor shift security left. Instead of waiting for a prompt injection to hit your LLM, Veritensor intercepts and sanitizes malicious documents, poisoned datasets, and compromised dependencies before they enter your Vector DB or execution environment.
Unlike standard SAST tools (which focus on code), Veritensor understands the binary and serialized formats used in Machine Learning:
requirements.txt, poetry.lock) for Typosquatting and known CVEs (via OSV.dev).@mcp.tool() functions. Scans claude_desktop_config.json and mcp.json for over-privileged permissions.LangChain, LlamaIndex, ChromaDB, and Unstructured.io to block threats at runtime.font-size: 0, color: white) and HTML comments. Veritensor scans raw binary streams to catch what standard parsers miss.pyproject.toml, poetry.lock, and Pipfile.lock for malicious packages (Typosquatting) and vulnerabilities.veritensor manifest . creates a signed JSON snapshot of your data artifacts for compliance (EU AI Act).SWdub3Jl... -> Ignore previous instructions)..exe renamed to invoice.pdf).--html flag.Veritensor is modular. Install only what you need to keep your environment lightweight (~50MB core).
| Option | Command | Use Case |
|---|---|---|
| Core | pip install veritensor | Base scanner (Models, Notebooks, Dependencies) |
| RAG | pip install "veritensor[rag]" | Documents (PDF, DOCX, PPTX) |
| PII | pip install "veritensor[pii]" | ML-based PII detection (Presidio) |
| AWS | pip install "veritensor[aws]" | Direct scanning from S3 buckets |
| All | pip install "veritensor[all]" | Full suite for enterprise security |
docker pull arseniibrazhnyk/veritensor:latest
Recursively scan a directory for all supported threats using 4 CPU cores:
veritensor scan ./my-rag-project --recursive --jobs 4
Check for Prompt Injections and Formula Injections in business data:
veritensor scan ./finance_data.xlsx
veritensor scan ./docs/contract.pdf
Create a compliance snapshot of your dataset folder:
veritensor manifest ./data --output provenance.json
Push your local security thresholds to the Enterprise Server:
veritensor scan . --sync-policy --api-key "vt_your_key"
Veritensor uses streaming to handle huge files. It samples 10k rows by default for speed.
veritensor scan ./data/train.parquet --full-scan
Ensure the file on your disk matches the official version from Hugging Face (detects tampering):
veritensor scan ./pytorch_model.bin --repo meta-llama/Llama-2-7b
Scan remote assets without manual downloading:
veritensor scan s3://my-ml-bucket/models/llama-3.pkl
Ensure the file on your disk matches the official version from the registry (detects tampering):
veritensor scan ./pytorch_model.bin --repo meta-llama/Llama-2-7b
Veritensor automatically reads metadata from safetensors and GGUF files. If a model has a Non-Commercial license (e.g., cc-by-nc-4.0), it will raise a HIGH severity alert.
To override this (Break-glass mode), use:
veritensor scan ./model.safetensors --force
Veritensor uses streaming to handle huge files. It samples 10k rows by default for speed.
veritensor scan ./data/train.parquet --full-scan
Check code cells, markdown, and saved outputs for threats:
veritensor scan ./research/experiment.ipynb
Create a standalone, interactive HTML dashboard of your scan results:
veritensor scan ./project --html
Detect dangerous tool logic and over-privileged permissions in your AI agent infrastructure:
# Scan MCP server Python files (AST analysis — no code execution)
veritensor scan ./mcp_servers/
# Also audit MCP configuration files
veritensor scan ./claude_desktop_config.json