bernstein
The open-source governance layer for AI agents. No model in the coordination loop, so replaying a plan reproduces its task graph byte-identically, and run receipts are byte-identical across independent builds. Signed lineage plus an opt-in HMAC audit chain a reviewer checks offline, without rerunnin
Findings (0)
✓ No registry-level findings. (This is a metadata scan, not a code audit.)
Embed this badge
[](https://vulnrable.com/mcp/bernstein/)
Automated registry-metadata scan; not a code audit. Findings come from PyPI metadata
published by the package owner and from public security advisories (OSV/GHSA) — not from our own
assessment of the code.
Grade scanned 2026-09-14 · package count resolved 2026-08-18.
A package fixed after that date will still show its earlier grade here.
Maintainer and think this is wrong or out of date? Get in touch — corrections are welcome.