A reference implementation of the SchemaPin protocol for cryptographically signing and verifying AI agent tool schemas to prevent supply-chain attacks.
It's less about the RAG exposing new data to a regular user, and more about using the vector pipeline as a covert channel. The idea is to sneak out data the attacker already can access, but in a way that might bypass traditional DLP looking at emails, USBs, etc.
The "fluff" is largely educational material, as the project is for research and learning. For a concrete technical demonstration, the scripts/embed.py and scripts/query.py scripts are the core, and the docs/guides/quick_start.md tries to offer a direct path to seeing it in action.
A comprehensive proof-of-concept demonstrating sophisticated vector-based data exfiltration techniques in AI/ML environments. This educational security research project illustrates potential risks in RAG systems and provides tools for defensive analysis.
