Back
A
Dev Security New · 2026-07-09

Agent Zero-Trust

Zero-trust pre-flight repo scanner for AI coding assistants: scans a codebase's instruction surface for prompt injection and supply-chain attacks before Claude Code, Cursor, Codex, or Gemini reads it. Ships with a false-negative ledger.

Visit site Open source via hn-showLast verified · 2026-07-09

AFIT Review

Accuracy
3.5
Privacy
5.0
Value
5.0
Multilingual
n/a
Ease of use
4.0
Scalability
3.0

Lab Verdict

A pre-flight security scan of your repo for Cursor / Claude Code / Codex. The engineering is disciplined: offline, deterministic, single-file, and the core never calls a model (which would make the scanner itself prompt-injectable). Ships a false-negative ledger and a threat model doc. Worth adding to the routine before an agent touches your codebase.

llm-judge · README review · 2026-07-09

Pricing

Open SourceFree

Capabilities

AI Coding AssistantSecurityZero TrustPrompt InjectionSupply ChainStatic AnalysisClaude CodeCursorOpen SourcePythonMIT