A Neon database branch for each Claude Code session: created from your default (or chosen) branch when the session starts, handed to every command Claude runs as DATABASE_URL, and set to expire on its own (or deleted when the session ends). Claude can migrate, seed and break the branch without touching production data. /neon shows it, keeps it or deletes it. Needs a Neon API key.
- Stars
- 33,859
- Version
- v2
- Copies
- 0
Overview
Waxell rates it high risk: 5 findings, highest severity high.
- Highest severity
- high
- Findings
- 5
- What ran
- Static analysis + deep scan
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
We don't republish the plugin's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked yesterday
Result
High risk Waxell rates it high risk: 5 findings, highest severity high.
Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work
Findings (5)
high · 3
- high
Agent Snooping: Agent Config Directory Access
README.md:58 · skillspector:AS1
- high
Tool Misuse: Tool Parameter Abuse
hooks/neon-api.ts:9 · skillspector:TM1
- high
Privilege Escalation: Credential Access
hooks/neon-branch-per-session.ts:16 · skillspector:PE3
medium · 2
- medium
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and pub
README.md:52 · skillspector:RP1
- medium
Agent Snooping: Skill Enumeration
README.md:56 · skillspector:AS3
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v2 (0.1.0)2026-11-163 changed High riskgot riskier
- v1 (0.1.0)2026-11-03 No issues
Files
Files
6 files, 35 KB in total. Names only; open them on GitHub.
- .claude-plugin/plugin.json
- README.md
- hooks/hooks.json
- hooks/neon-api.ts
- hooks/neon-branch-per-session.ts
- tests/neon-branch-per-session.test.ts
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More engineering skills and plugins
rex-ttydavila7Inside the Rex terminal, runs the Bash commands that need a real terminal (sudo, gh auth login, git rebase -i, a key passphrase) in a Rex… High riskEngineeringAI & agents34k
jev-auto-modedavila7A permission layer driven by a JSON policy: allow, ask or deny every tool call (Bash, edits, web, MCP, subagents, skills), every slash… High riskEngineeringAI & agents34k
jev-guardrailsdavila7Screens every prompt going into the conversation and every reply coming out of it with TypeSafe's Jev, a System One decision model, the… High riskEngineeringDocuments34k
jev-vercel-sandboxdavila7A Vercel Sandbox Claude sends work to on purpose: long test runs in the background, someone else's repository, an installer of unknown… High riskEngineeringDocuments34k