Waxell

plugin

jev-guardrails High risk

davila7davila7/claude-code-templatesupdated

Screens every prompt going into the conversation and every reply coming out of it with TypeSafe's Jev, a System One decision model, the way TypeSafe's guardrails cookbook does: one request per message asks a battery of hazard questions (jailbreak, harm or a crime, a diagnosis or a dosage, self-harm) and scores how much harm complying would do. The thresholds live here, in a named policy (strict or permissive), and turn the probabilities into pass, review (the user is asked), block (the prompt is dropped, or the reply withheld) or support. Falls back to the engine's built-in classifier when…
davila7's own description, from the plugin's files.
Stars
33,859
Version
v2
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 12 findings, highest severity high.

Highest severity
high
Findings
12
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: 12 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 (12)

high · 4

  • high

    Anti-Refusal: Anti-Refusal Statement

    README.md:60 · skillspector:AR2

  • high

    Agent Snooping: Agent Config Directory Access

    README.md:96 · skillspector:AS1

  • high

    Agent Snooping: Agent Config Directory Access

    README.md:129 · skillspector:AS1

  • high

    Anti-Refusal: Anti-Refusal Statement

    hooks/policy.ts:452 · skillspector:AR2

medium · 8

  • medium

    Data Exfiltration: External Transmission

    README.md:79 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    hooks/policy.ts:17 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    tests/policy.test.ts:229 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    tests/policy.test.ts:229 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    tests/policy.test.ts:280 · skillspector:E1

  • medium

    Data Exfiltration: External Transmission

    tests/policy.test.ts:281 · skillspector:E1

  • 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:142 · skillspector:RP1

  • medium

    Agent Snooping: Skill Enumeration

    README.md:151 · skillspector:AS3

Versions

Version history

Each distinct content we have seen, newest first, with the verdict it got at the time.

  1. v2 (0.1.0)2026-11-162 changed High riskgot riskier
  2. v1 (0.1.0)2026-11-03 No issues

Files

Files

6 files, 71 KB in total. Names only; open them on GitHub.

  • .claude-plugin/plugin.json
  • README.md
  • hooks/hooks.json
  • hooks/jev-guardrails.ts
  • hooks/policy.ts
  • tests/policy.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

See all