AltimateAI / AltimateAI/altimate-code
test: behavioral regression test that MCP tool calls enforce the permission check
Đang mở
- Ngôn ngữ chính
- TypeScript
- Star
- 811
- Fork
- 134
- Merge trung bình
- 3 ngày 2 giờ
- Pull request đã merge (30 ngày)
- 50
Mô tả
Found during v0.9.1 release review (CTO + Tech-Lead). The security fix e7ec6a9b29 (MCP tools ran with NO permission check — an Effect awaited but never run) has only grep-for-string coverage (`v140-merge-adversarial.test.ts`), which would pass even with the bug present. Add a test that drives an MCP tool call end-to-end through `session/prompt.ts` and asserts `PermissionNext.ask` is actually invoked / the call is gated. Prevents silent reintroduction on refactor.
Hướng dẫn đóng góp
Đánh giá
Issue này chưa được đánh giá.