# Umanitek's Agent Blackbox v1.2.0 joins Hermes plugin catalog

> Original title: Agent Blackbox v1.2.0 from @umanitek is now live in the @NousResearch Hermes plugin catalog.

- Source: X search: AI launch posts (introducing, just launched)
- Published: 2026-11-07T10:45:39.000Z
- Bad Influence: https://badinfluence.news/items/ba83t232zxta0c30h8nwava6g
- Original: https://x.com/woisau1/status/2119018435246231687

## Summary

Umanitek says Agent Blackbox v1.2.0 is now live in the Hermes plugin catalog from Nous Research. The plugin checks every tool call and model request an AI agent makes against a verified threat graph on the OriginTrail DKG before it runs. It covers prompt injection, dangerous commands, malicious packages, unsafe skills, and attempts on wallets and keys, and can either audit or block.

## Post

Agent Blackbox v1.2.0 from @umanitek is now live in the @NousResearch Hermes plugin catalog.

It checks every tool call and model request an AI agent makes before it runs, against a verified threat graph on the @origin_trail DKG.

$TRAC
https://x.com/umanitek/status/2118681388828270711

## Quoted post @umanitek

> Agent Blackbox v1.2.0 is live in the Hermes plugin catalog 🛡️ 
> 
> Thank you @Teknium and @NousResearch!
> 
> Already running Hermes (Desktop too)?
> 
> #Blackbox checks every tool call and model request your #AI agent makes before it runs, against our verified threat graph on the @origin_trail #DKG. 
> 
> ✅ - Prompt injection, 
> ✅ - Dangerous commands, 
> ✅ - Malicious packages, 
> ✅ - Unsafe skills, and 
> ✅ - Attempts on your wallets and keys. 
> ✅ - Audit mode records, block mode refuses.

https://x.com/umanitek/status/2118681388828270711