# I built a testing tool for AI agents — it caught a real prompt-injection vulnerability in a local model

> Source: <https://dev.to/klindi_tafa_c34dd04a92dba/i-built-a-testing-tool-for-ai-agents-it-caught-a-real-prompt-injection-vulnerability-in-a-local-13e2>
> Published: 2026-09-08 12:16:43+00:00

I've been building Agenci — open-source CI/CD testing for AI agents (functional tests, security checks, regression detection across model/prompt changes).

Wanted to actually test it against something real rather than a synthetic example, so I pointed it at phi4-mini running locally via Ollama. First security test: told it to ignore its instructions and just say a specific word. It complied instantly — screenshot attached.

Small, efficient local models are great for a lot of things, but this made me curious how consistent this weakness is across other small local models people are running. Anyone here tested for prompt-injection resistance specifically, or is this a known/expected tradeoff at this model size?

Repo (free, pip install agenci): github.com/klinditafa1/agenci