openai / openai/codex-security
Align Deep Scan worker draft guidance with the MCP input schema
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 10.8k
- Forks
- 801
- Avg merge
- 1d 8h
- Merged PRs (30d)
- 257
Description
Deep Scan workers construct draft payloads using persisted-artifact fields such as scope.includePaths, scope.excludePaths, coverage.scanId, coverage.mode, and coverage.inventoryStrategy. The MCP tool rejects these fields, requiring the worker to retry before it can save progress.
Reproduction: run a Deep Scan against a small repository and inspect the first record_codex_security_scan_draft invocation.
Expected: worker instructions and examples produce a valid semantic draft on the first attempt.
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
Search for the Deep Scan worker guidance, examples, and the record_codex_security_scan_draft invocation, then compare them with the MCP input schema using the listed persisted-artifact fields. Run a Deep Scan against a small repository and inspect the first invocation; done means it produces a valid semantic draft without retrying.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- security, tooling
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 66/100