How Secrets Leak Through AI Agents (and How to Stop It) — Venice AI
Joshua Mo, lead developer relations engineer at Venice AI and previously lead maintainer of the Rust AI framework Rig, explains why privacy matters (one breach and users leave, and less stored data means a smaller blast radius) and how Venice approaches it: no stored prompts, anonymized requests to closed providers, models in trusted execution environments, and split-key encrypted storage.
Proof1 independent outlet
Key points
- A private model doesn't make a private product.
- The leaks happen in everything you build around it.
- His patterns: hashed IDs instead of personal data, split-key custody, revocable handles, narrow agent scope, a classifier in front of the agent to catch prompt injection, wiring the vault to the execution layer instead of the LLM, sandboxes plus permission monitoring, and confidential compute with verifiable attestations.
- • How logs and secrets leak through a typical agent
Sources (1)
- [1]How Secrets Leak Through AI Agents (and How to Stop It) — Venice AIAI Engineer (YouTube) · Oct 11, 04:30 PM
Joshua Mo, lead developer relations engineer at Venice AI and previously lead maintainer of the Rust AI framework Rig, explains why privacy matters (one breach and users leave, and less stored data means a smaller blast radius) and how Venice approaches it: no stored prompts, anonymized requests to closed providers, models in trusted execution environments, and split-key encrypted storage.
A private model doesn't make a private product.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 11, 2026Can Your Agent Hear You Now? Building Live Voice Agents with Gemini — Thor Schaeff
- Oct 11, 2026Agents That Own Their Inference — Du'an Lightfoot & Khaja Omer, Akamai Technologies
- Oct 11, 2026AI Security Engineer Foundations + Certificate — Micah Silverman, Snyk
- Oct 11, 2026The Data Context Layer for Agents — Yoni Michael & Brandon Callender, Typedef
- Oct 8, 2026Microsoft Joins the Local AI Push
- Oct 8, 2026Beyond Imitation: A Framework and Benchmark for LLM-Assisted Peer Review