See what your employees are prompting LLMs (without network proxies)

Name: See what your employees are prompting LLMs (without network proxies)
Availability: InStock
Author: asilozyildirim

by asilozyildirim·Apr 9, 2026·4 points·0 comments

Visit Project View on HN

AI Analysis

●MidBold Bet

Another AI security wrapper in a crowded market, but agent-side integration is interesting.

Strengths

•Embeds into agent frameworks like LangGraph to intercept data before transmission.
•Requires no network proxies, deploying via lightweight extension or MDM push.

Weaknesses

•Vague technical details on scoring algorithms compared to established competitors.
•Enterprise security market is saturated with well-funded players like Lakera.

Post Description

Hey HN,

Most enterprises are "shadow-prompting"—employees use personal accounts on Gemini/ChatGPT/Claude, and security teams have zero visibility. We saw the recent reports on malicious extensions harvesting these prompts and decided to build a "defensive" version.

It’s a lightweight Chromium extension for Privent. No heavy proxies or network changes. It categorizes outgoing data and scores risk locally.

We’re keeping it 100% free because we want to see the actual scale of data leakage across different industries. We're looking for 10 teams to run a pilot this week and get a 24-hour visibility report.

Demo: https://cal.com/asilozyildirim/30min Trust: https://trust.privent.ai/