MOAR AI def issues
Open
Nobody has claimed this yet.
New Challenge
- Dominant language
- HTML
- Stars
- 1.5k
- Forks
- 625
- Avg merge
- 14h 21m
- Merged PRs (30d)
- 44
Description
Context
- What should the challenge scenario be like?
Agent instruction/context files: CLAUDE.md, AGENTS.md, .cursor/rules, .windsurfrules, etc. can contain real credentials added as persistent context and then accidentally committed. This generalizes the skill-file challenge to the wider ecosystem. We already have skills.md so now we need to add it to others. - What should the participant learn from completing the challenge?
be careful what you put in agents.md/rules/etc. - For what category would the challenge be? (e.g. Docker, K8s, binary)
AI
Did you encounter this in real life? Could you tell us more about the scenario?
yes
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 reviewing the existing skills.md challenge and compare it with the agent instruction/context filenames listed in the issue: CLAUDE.md, AGENTS.md, .cursor/rules, and .windsurfrules. Add a corresponding AI challenge showing how credentials in these files can be accidentally committed, with completion teaching participants to avoid placing secrets there.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai-infra-agents, security
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100