AI-triage should have separate steps for analyzing and executing code
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3
- Forks
- 5
- Avg merge
- 1d 9h
- Merged PRs (30d)
- 2
Description
The AI assistant implemented in https://github.com/ubuntu/startriage/pull/3 has on_permission_request=PermissionHandler.approve_all set; this may be dangerous when running on a non-isolated environment.
The safe way would be separating the triage task in two main steps, as described in https://github.com/ubuntu/startriage/pull/3#pullrequestreview-4562181569
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
Start with pull request #3 and its review comment, which describe the current AI assistant and the proposed separation. Trace how triage currently analyzes and executes code, then confirm that analysis can occur without automatic permission approval before treating the work as done.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, security
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100