sparkBLOCK
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.
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.
6b58edc143d7OBSERVED · 2026-10-13What 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: "adversary" description: "Show CocoAdversary reviewer configuration and latest challenge results." version: "2.0.1" author: "CocoPlus" tags: - cocoplus - cocoadversary --- Your objective is to implement `$adversary`. Before proceeding, verify that `.cocoplus/` exists. If not, output: "CocoPlus not initialized in this directory. Run `$pod init` to begin." Then stop. Read `.cocoplus/modes/adversary.on`, `.cocoplus/adversary/config.json`, and recent adversary reports. Summarize enabled state, configured challenge depth, latest high-severity finding, and known gaps. Available subcommands: `$adversary enable`, `$adversary disable`, `$adversary run`, `$adversary show`, `$adversary audit`, `$adversary gap`. ## Anti-Rationalization | Shortcut / Temptation | Why It Fails | |-----------------------|--------------| | Treat the skill as complete because the file exists | Skill contracts must describe observable behavior and verification, not just command names. | | Skip artifact and safety checks for a small command | Small commands still mutate state or guide execution; preserve the same gates. | ## Exit Criteria - [ ] Command behavior matches the owning feature contract. - [ ] Required reads, writes, and user-visible outputs are described. - [ ] Safety, governance, and artifact constraints are preserved. - [ ] Missing state produces a clear, non-destructive result.
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
- Security controls (access validation, credential handling, injection defense)
- If the LLM synthesis call fails (access error, timeout, rate limit, credential constraint):
description: "Activate and manage Leviathan God Mode and Ronin companion state. Supports `$leviathan on/off/status/learn`."
Gates applied: no_behavioural_pass.
6b58edc143d7full audit observations/trust-audit/skill/snowflake-labs__skills.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-13 | 6b58edc143d7 | BLOCK | D | 69 | first audit |
Questions
What does the spark 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 spark safe to install?
No — not without reading the findings first. The audit graded it D (69/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What can spark 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.