Atlas / Skills / snowflake-labs / Safety Gate

Safety GateSAFE

skills/snowflake-labs/safety-gate

CocoPlus is an Agentic Operating System for Snowflake Coco. It brings structured, multi-agent workflows to data engineering projects — covering everything from project initialization through spec, plan, build, test, review, and ship phases.

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
1.0.0
Hosts
—
License
MIT
Stars
724
01

Overview

CocoPlus is an Agentic Operating System for Snowflake Coco. It brings structured, multi-agent workflows to data engineering projects — covering everything from project initialization through spec, plan, build, test, review, and ship phases.

Read from source at commit 6b58edc143d7OBSERVED · 2026-10-13
Advertisement
02

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: "safety-normal"
description: "Set Safety Gate to normal mode. In normal mode, destructive SQL operations trigger a soft-gate confirmation prompt before execution. Recommended for development environments."
version: "1.0.0"
author: "CocoPlus"
tags:
  - cocoplus
  - safety-gate
---

Your objective is to set the Safety Gate to normal mode.

Before proceeding, verify that `.cocoplus/` exists.
If not: output "CocoPlus not initialized in this directory. Run `$pod init` to begin." Then stop.

Remove any existing safety mode flags (cross-platform using the Bash tool):
```
node -e "['safety.strict','safety.off'].forEach(f=>{try{require('fs').unlinkSync('.cocoplus/modes/'+f)}catch(_){}});console.log('Old flags cleared.');"
```

Create normal mode flag: create the file `.cocoplus/modes/safety.normal` with empty content using the Write tool.

Update AGENTS.md (keep ≤200 lines): replace Safety line with `- Safety: normal (WARN + confirm for destructive SQL)`

Output: "✓ Safety Gate set to NORMAL. Destructive SQL operations will require explicit confirmation before execution. This setting persists across sessions."

## Anti-Rationalization

| Shortcut / Temptation | Why It Fails |
|-----------------------|--------------|
| Keep strict/off flags while enabling normal | Mixed flags create unpredictable gate decisions |
| Skip warning semantics in the summary message | Developers may mistake normal mode for full blocking |
| Avoid updating AGENTS.md to save time | Runtime posture becomes opaque to the team |

## Exit Criteria

- [ ] `.cocoplus/modes/safety.normal` exists
- [ ] `.cocoplus/modes/safety.strict` and `.cocoplus/modes/safety.off` do NOT exist
- [ ] `.cocoplus/AGENTS.md` Safety line reads `- Safety: normal (WARN + confirm for destructive SQL)`
- [ ] Confirmation output states normal mode is active with warning + confirmation behavior
03

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

Audited 2026-10-13 · audit v0.4.1 · source sha 6b58edc143d7full audit observations/trust-audit/skill/snowflake-labs__safety-gate.json · Report an issue / request a re-scan
04

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-136b58edc143d7SAFEB89first audit
05

Questions

What does the Safety Gate skill do?

CocoPlus is an Agentic Operating System for Snowflake Coco. It brings structured, multi-agent workflows to data engineering projects — covering everything from project initialization through spec, plan, build, test, review, and ship phases.

Is Safety Gate 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 Safety Gate access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

How current is this page?

The grade is for one exact copy of the source (6b58edc143d7), read on 2026-10-13. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement