openedx / openedx/openedx-ai-extensions
Prevent prompt injection on educator workflow extra_instructions
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17
- Forks
- 11
- Avg merge
- 5h 33m
- Merged PRs (30d)
- 4
Description
It is to change all instruction via https://github.com/openedx/openedx-ai-extensions/blob/main/backend/openedx_ai_extensions/prompts/default_generate_quiz_questions.txt EXTRA_INSTRUCTIONS
Contributor guide
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 by reading backend/openedx_ai_extensions/prompts/default_generate_quiz_questions.txt, especially the EXTRA_INSTRUCTIONS section, and trace where this prompt is used in the educator workflow. Clarify the intended prompt-injection protection and verify that the resulting workflow no longer allows extra instructions to override its intended behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, security
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100