Home › AI Agents & LLM Tools › Weir
Weir
Catch credential leaks in the AI agents you build and use
| Built with | AI (tool not stated) |
|---|---|
| Category | AI Agents & LLM Tools |
| Maker | CodeNinja778 |
| Launched | 2026-10-27 |
| Source | Hacker News Show HN · 3 points |
| Link checked | 2026-11-02 |
How we know it was built with AI
- AI (tool not stated): “Built with AI”
Quoted from the source post. Category is assigned automatically.
From the maker
Hi HN. Weir is for one problem: credentials crossing the boundaries of your AI agent. For agents you build, Weir plants fake credentials where real ones would live, runs the agent's normal flows, and checks what comes out: telemetry, logs, console output, model requests, and requests to other services.
From the website
Keep your sensitive credintials out of the agents you build and the coding agent you use. Test any agent with planted fake keys, or see which of your real keys a Claude Code session exposed. - IdoG...
Similar apps
pw-repl
A Playwright-powered REPL for you and your agents to share
SlopGrid
Create your own oneshot AI model benchmarks
chromewebstore.google.com
Rename Super Intelligence Back to Artificial Intelligence
WattzGOAT
An intentionally vulnerable web app for security training
Proxima Forma
Designs that my AI agents understand
Sokit
A LangChain like harness for Jev (or other System 1 models)