[Feature] Add RAG retrieval poisoning test scenarios

Open
#2,156 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
52/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Active
Tech stack
python

Research direction

Start by reviewing related issue #2085 and the existing scenario library and attack executor. Add pyrit/scenario/scenarios/rag_retrieval_poisoning.py with predefined retrieval-poisoning attack vectors and scenario docstrings. The work is done when the scenarios are integrated with the existing executor and documented in the new file.

Written by the indexing model from the issue text.

Description

Summary

Add built-in test scenarios for RAG retrieval poisoning attacks to PyRIT's scenario library.

Problem

RAG systems are vulnerable to retrieval poisoning where malicious content is injected into the knowledge base. PyRIT currently lacks dedicated scenarios for testing this attack surface.

Proposed Implementation

  • New file: pyrit/scenario/scenarios/rag_retrieval_poisoning.py
  • Predefined attack vectors for retrieval poisoning
  • Integration with existing attack executor
  • Documentation in scenario docstrings

Use Case

Security teams can use these scenarios to test RAG-based LLM applications against known poisoning attack patterns.

References

  • Related: issue #2085
Dominant language
Python
Stars
4.5k
Forks
896
Avg merge
3d 7h
Merged PRs (30d)
155

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.

More from microsoft/PyRIT

All issues in microsoft/PyRIT

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.