jevbooks

← All projects

is-malicious

luantak/is-malicious

Scan a codebase for malicious behavior with TypeSafe Jev.

Verification & Guardrails85%Runner-up: Content Moderation

What it is

A CLI and GitHub Action that scans source, configuration, build, and CI files for hidden, deceptive, or data-stealing behavior, giving a second opinion before running unfamiliar code.

How it uses Jev

Jev reviews file contents for behavior and context using all check categories in one request. Suspicious or uncertain chunks get a second pass focused on line windows Jev identified. Findings list file, line range, category, probability, and confidence.

Primitives:choicescorenoul

Technique worth stealing

Escalate suspicious or uncertain chunks to a second Jev pass focused on the line windows the first pass identified.

Try it

export TYPESAFE_API_KEY=your-api-key; npx is-malicious /path/to/project

View on GitHub

judged by Jevjev-1.13.0

Evidence

Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.

  • Jev-centricyes0.94
  • Shows a System One patternunclear0.60
  • Handles uncertaintyno0.14
  • Measuredno0.09
  • Runnableyes0.98
  • Worth recommendingno0.37
  • Model replicano0.03
  • Problem scopescore on a 0–2 scale1.93
  • About Jevyes0.97

Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.