Suggestion: Add pre-built MITRE ATLAS technique mapping for orchestrators
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 4.5k
- Forks
- 893
- Avg merge
- 3d 50m
- Merged PRs (30d)
- 165
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.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
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.
Assessment
- Tech stack
- python
- Domain
- ai, security
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100