luzra-cli@0.1.11
터미널 AI(Claude Code) 프롬프트 습관을 채점·코칭하는 리포트 — 세션 로그는 로컬에서만 분석됩니다.
AI Security Review
scanned 3mo ago · by lpm-firewall-aiThe flagged primitives implement the documented CLI workflow and are reached through explicit commands, not install hooks. No stealth execution, foreign AI-agent control-surface mutation, credential harvesting, or unconsented exfiltration was found.
Static reason
One or more suspicious static signals were detected.
Trigger
User runs luzra init, report, connect, or sync.
Impact
Creates ~/.luzra data and an optional daily report scheduler; sends configured report data to the selected dashboard.
Mechanism
User-invoked session analysis, scheduled reporting, and configured dashboard sync.
AI rationale
The flagged primitives implement the documented CLI workflow and are reached through explicit commands, not install hooks. No stealth execution, foreign AI-agent control-surface mutation, credential harvesting, or unconsented exfiltration was found.
Evidence
package.jsonbin/luzra.jssrc/init.jssrc/engine.jssrc/sync.jssrc/schedule.jssrc/masking.js~/.claude/projects~/.luzra/config.json~/.luzra/state.json~/.luzra/reports/profile.json~/Library/LaunchAgents/ai.luzra.daily.plist~/.config/systemd/user/luzra.service~/.config/systemd/user/luzra.timer
Network endpoints5
luzra.aimgonna.com/api/device/startluzra.aimgonna.com/api/device/pollluzra.aimgonna.com/api/assetsluzra.aimgonna.com/api/scoresluzra.aimgonna.com/api/sync
Decision evidence
public snapshotAI called this Clean at 90.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
Evidence against
- No lifecycle scripts in package.json.
- bin/luzra.js only dispatches user-invoked commands.
- src/init.js performs global install and scheduling only during explicit init.
- src/sync.js uploads configured scoring/profile data only after device connection.
- src/engine.js masks common secrets before passing prompts to Claude CLI.
Behavioral surface
ChildProcessEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
NoLicense
Source & flagged code
6 flaggedsrc/connect.jsView file
1// 디바이스 코드 페어링 — 토큰을 사람이 복사·전달할 필요가 없다.
L2: import { spawn } from "node:child_process";
L3: import { c, blank, info, ok, warn } from "./ui.js";
High
1// 디바이스 코드 페어링 — 토큰을 사람이 복사·전달할 필요가 없다.
L2: import { spawn } from "node:child_process";
L3: import { c, blank, info, ok, warn } from "./ui.js";
L4:
L5: export const DEFAULT_URL = "https://luzra.aimgonna.com";
L6:
...
L8: const cmd =
L9: process.platform === "win32" ? ["cmd", ["/c", "start", "", url]]
L10: : process.platform === "darwin" ? ["open", [url]]
...
L23: headers: { "Content-Type": "application/json" },
L24: body: JSON.stringify(body || {}),
L25: });
High
Sandbox Evasion Gated Capability
Source gates dangerous network, credential, or execution behavior behind CI, host, platform, time, or geo fingerprint checks.
src/connect.jsView on unpkg · L1src/install.jsView file
16// Windows의 npm은 npm.cmd라 shell이 필요하다. 인자를 배열로 주면 경고가 나므로 문자열로 넘긴다.
L17: const r = spawnSync("npm root -g", { encoding: "utf-8", shell: true });
L18: const dir = (r.stdout || "").trim();
Findings
5 High4 Medium4 Low
HighChild Processsrc/connect.js
HighShellsrc/install.js
HighSandbox Evasion Gated Capabilitysrc/connect.js
HighTrigger Reachable Persistencesrc/schedule.js
HighRuntime Package Installsrc/install.js
MediumNetwork
MediumEnvironment Vars
MediumInstall Persistencesrc/schedule.js
MediumStructural Risk Force Deep Review
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
LowNo License
Affected versions and remediation
This report applies to luzra-cli@0.1.11.
See all versions of luzra-cli for other recorded verdicts.
- Review the evidence and your use of luzra-cli@0.1.11 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.