Agent skill · Audited from source

Bernstein Approve

skill · sipyourdrink-ltd/bernsteinApache-2.0 licenceAudited 14 Oct 2026 · source 6ba64a7d2489

★ 1,237pushed today
✓SAFEGrade B · 89/100 · 14 Oct 2026 · 6ba64a7
1,237repo stars · whole sipyourdrink-ltd/bernstein

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 6ba64a7d2489 and observed network access and no hard-coded secrets. What it does: Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent work, or needs to approve/reject a plan before execution begins.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Bernstein Approve (sipyourdrink-ltd/bernstein)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/sipyourdrink-ltd/bernstein-approve

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high1 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkDeclared6 observations
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeWARN1
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (1)

MEDIUMNetwork egressnet.raw_ip · scripts/approvals.sh:12
F-04 Network egressCWE-200 · CWE-319Layer L1
API="${BERNSTEIN_API_URL:-http://127.0.0.1:8052}"
Why
No further detail recorded for this rule.
Fix
—

Audit 0.4.1 · source sha 6ba64a7d2489 · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishersipyourdrink-ltd GitHub organizationOwner of the repository this skill is read from
  • Source foldersipyourdrink-ltd/bernstein/packages/cursor-plugin/skills/bernstein-approveThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdict6ba64a7d2489A new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent work, or needs to approve/reject a plan before execution begins.

---
name: bernstein-approve
description: >
  Review and approve/reject pending tasks or plans in Bernstein.
  Use when the user asks about approvals, wants to review agent work,
  or needs to approve/reject a plan before execution begins.
---

# Bernstein Approvals

Review pending approvals and plans, then approve or reject them.

## When to Use

- User asks "any pending approvals?" or "what needs my review?"
- User wants to approve or reject a completed task
- User wants to review and approve/reject a plan before agents execute it
- User says "approve that" or "reject task X"

## Instructions

### List pending approvals

1. Run `scripts/approvals.sh list` to fetch pending approvals and plans.
2. Present each item with its diff summary and test results:

```
## Pending Approvals

### Task TASK-042: Fix auth middleware
**Agent:** claude-backend-01 | **Role:** backend
**Files changed:** src/auth/middleware.py (+42 -8)
**Tests:** 14/14 passing

[Approve] [Reject]
```

### Approve or reject

3. When the user decides:
   - Approve: `scripts/approvals.sh approve <task_id> "reason"`
   - Reject: `scripts/approvals.sh reject <task_id> "reason"`

4. For **plans** (multi-task proposals):
   - List plans: `scripts/approvals.sh plans`
   - Approve plan: `scripts/approvals.sh approve-plan <plan_id>`
   - Reject plan: `scripts/approvals.sh reject-plan <plan_id>`

### After approval

5. Confirm the action and note what happens next:
   - Approved tasks → agent commits and merges
   - Approved plans → planned tasks promoted to open, agents start picking them up
   - Rejected → task goes back to open for retry, or gets cancelled

Excerpt, first 1,639 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 6ba64a7

Download folder ↗
git clone https://github.com/sipyourdrink-ltd/bernstein
git -C bernstein checkout 6ba64a7d2489

The author documents no install command, so this uses the repository directly. Our verdict covers commit 6ba64a7d2489 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 6ba64a7d2489

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/sipyourdrink-ltd/bernstein-approve/badge.svg)](https://modelsatlas.com/skills/sipyourdrink-ltd/bernstein-approve/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/sipyourdrink-ltd/bernstein-approve/badge.svg)](https://modelsatlas.com/skills/sipyourdrink-ltd/bernstein-approve/)

Questions about Bernstein Approve

What does the Bernstein Approve skill do?
The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run
Is Bernstein Approve safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Bernstein Approve access on my machine?
The audit observed that it reaches the network. Each of those is consistent with what it says it does. Secrets in the source: none found.
How current is this page?
The grade is for one exact copy of the source (6ba64a7d2489), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.