@hyuga/llm-safe-sql
MITLet 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.
100
Security score
0 known advisories in v0.8.0
Weekly downloads
—
Unpacked size
1.1 MB
Dependencies
0
Last publish
11 hours ago
Security advisories
No known vulnerabilities affect v0.8.0.