proventra/proventra-core

Secure your AI Agents against prompt injection attacks

33
/ 100
Emerging

This tool helps developers protect their AI agents or large language model (LLM) applications from malicious instructions. It takes user input intended for an LLM, identifies harmful 'prompt injection' attempts, and can either flag them or rewrite the input to remove the unsafe parts. Any developer building an LLM-powered application where users can provide free-form text input would benefit from this.

No commits in the last 6 months. Available on PyPI.

Use this if you are developing an AI agent or LLM application and need to filter or clean user input to prevent it from being tricked or exploited.

Not ideal if you are an end-user of an AI application and not involved in its development, or if you need to protect against general cybersecurity threats outside of prompt injection.

AI-security LLM-application-development prompt-engineering input-validation agent-safety
Stale 6m
Maintenance 2 / 25
Adoption 6 / 25
Maturity 25 / 25
Community 0 / 25

How are scores calculated?

Stars

19

Forks

Language

Python

License

MIT

Last pushed

Apr 24, 2025

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/proventra/proventra-core"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.