@hyuga/llm-safe-sql
Let an LLM propose UPDATE/DELETE, then actually run it, measure the real before/after diff, and always roll back — so the human approves measured facts, not the model's claim.
as observed 2026-09-04T08:09:22.439Z- Identifier
@hyuga/llm-safe-sql- Source
- npm
- Version observed
- 0.11.0
- Source repository
- https://github.com/hyuga611/airframe
- Repository observation
- Commits observed in the last 90 days
- First observed here
- 2026-09-02T06:49:03.099Z
- Observations recorded
- 2
- Weekly downloads (upstream)
- 241
- Publish rights held by
- hyuga
- Declared license
- MIT
Observation history
2026-09-04T08:09:22.439Z
Fields that differed: version
| Field | Before | After |
|---|---|---|
version |
"0.10.1" | "0.11.0" |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.