RocketChat / RocketChat/Apps.QuickReplies

[Feat] : Security system for LLM

Open
#53 10 comments 0 reactions 1 assignee View on GitHub

@thekishandev is already working on this.

Since Mar 30, 2025.

enhancement
Dominant language
TypeScript
Stars
7
Forks
21
PR merge metrics
No merged PRs in 30d

Description

What do we need?

Right now, anyone can type anything into the prompt and receive a response.

This should not happen—AI should not reply with anything inappropriate or unprofessional.

Acceptance Criteria
  • Add a prompt sent with all AI-related API calls.
  • Create a new prompt to ensure that AI does not respond to inappropriate inputs but provides a common response in such cases.
  • Handle all other cases where the LLM may generate incorrect or undesired responses.
Relevant ScreenShots

No response

Further Comments

No response

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.