Suggestion: Add pre-built MITRE ATLAS technique mapping for orchestrators

Open
#2,084 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
35/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Quiet
Tech stack
python
Domain
ai, security

Research direction

No files or tests are identified in the issue. Start by reviewing PyRIT's orchestrator implementations and the MITRE ATLAS technique taxonomy, then define how mappings should be represented and attached to generated attack scenarios. Done means supported orchestrator outputs carry accurate ATLAS technique IDs for reporting.

Written by the indexing model from the issue text.

Description

PyRIT's orchestrators currently generate attack scenarios without explicit mapping to MITRE ATLAS tactics/techniques. For practitioners running systematic AI red team assessments, having each orchestrator's output automatically tagged with the corresponding ATLAS technique ID (e.g., AML.T0051 for prompt injection) would make reporting and compliance mapping significantly easier, especially for teams that need to present findings against a recognized framework. Would be happy to contribute example mappings if useful.

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.