registry / AI-agent capability abuse / triflux / 10.67.1

triflux@10.67.1

CLI-first multi-model orchestrator for Claude Code — route tasks to Codex, Antigravity, and Claude

AI Security Review

scanned 10d ago · by lpm-firewall-ai

The source shows a real dangerous capability: tfx-live defaults to launching or resuming Codex without normal approval and sandbox protections, and its default flow can accept folder trust. Because these behaviors are package-aligned and user-command activated, with no verified credential theft or payload delivery, warn rather than block.

Static reason

High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review

Trigger

Installing the package through npm activates postinstall setup; running tfx-live start or resuming a Codex session activates the elevated launch behavior.

Impact

Codex can act without its normal approval or sandbox controls and may receive folder trust automatically. The inspected source does not establish credential theft or a broader control hijack.

Mechanism

Setup copies package files into the user's Claude configuration and registers Codex session hooks without granting trust. The live launcher uses its default high-privilege Codex command and handles folder-trust prompts unless --no-auto-trust is supplied.

AI rationale

Evidence

package.jsonscripts/setup.mjsscripts/ensure-codex-hooks.mjsbin/tfx-live.mjs

Decision evidence

public snapshot

AI called this Suspicious at 94.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

package.json runs scripts/setup.mjs at postinstall; registry installs take the deferred setup path, which copies package files into the user's .claude configuration and invokes setup's consent routine.
During setup, the package registers its Codex session hooks without granting trust; the code defers hook approval when it cannot ask the user.
On tfx-live start, the default Codex launch and resume commands bypass approval and sandbox protections. The launcher only accepts --sandbox for Antigravity.
By default, the launcher processes Codex folder-trust screens and confirms an affirmative selection; --no-auto-trust changes that path to a blocking screen.
The other supplied integration locations refer to local Claude and Codex configuration, package-owned cleanup, model state, or local diagnostics. Inspection did not establish credential transfer or an unrelated remote recipient there.

Evidence against

The observed risk is tied to package setup and explicit live-session commands; inspected source did not establish credential theft, arbitrary payload delivery, or a malicious network transfer.
Codex hook registration leaves the hook untrusted when interactive approval is unavailable.

Source & flagged code

25 flagged

package.jsonView file

Lines 1-37json

2 "name": "triflux",

3 "version": "10.67.1",

4 "description": "CLI-first multi-model orchestrator for Claude Code — route tasks to Codex, Antigravity, and Claude",

5 "type": "module",

6 "bin": {

7 "triflux": "bin/triflux.mjs",

8 "tfx": "bin/triflux.mjs",

9 "tfx-live": "bin/tfx-live.mjs",

10 "tfx-setup": "bin/tfx-setup.mjs",

11 "tfx-doctor": "bin/tfx-doctor.mjs"

12 },

13 "engines": {

14 "node": ">=22"

15 },

16 "scripts": {

17 "postinstall": "node scripts/setup.mjs"

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg · L17

18 },

19 "dependencies": {

20 "@iarna/toml": "^2.2.5"

21 },

22 "files": [

23 "adapters",

24 "bin",

25 "config",

26 ".claude/rules/tfx-routing.md",

27 "skills",

28 "!skills/tfx-workspace",

29 "hooks",

30 "hud",

31 "scripts",

32 "!scripts/__tests__",

33 "hub",

34 "docs/assets/logo-dark.svg",

35 "docs/assets/logo-light.svg",

36 "docs/assets/social-preview.png",

37 "docs/assets/social-preview.svg",

bin/tfx-live.mjsView file

Lines 1-21javascript

1#!/usr/bin/env node

2import { execFile } from "node:child_process";

3import { randomBytes } from "node:crypto";

High

Child Process

Package source references child process execution.

bin/tfx-live.mjsView on unpkg · L1

4import {

5 existsSync,

bin/triflux.mjsView file

Lines 1503-1543javascript

1503 persistSettings(settings, settingsPath);

1504 report.alreadyInGoalState = false;

1505 }

1506 } else

1507 addWarning(report, "statusline", "HUD 파일 없음: 먼저 파일 동기화 필요");

1508

1509

scripts/lib/install-retire.mjsView file

Lines 29-69javascript

29 /^synapse-sessions\.json$/,

30 /^team-native-.+\.json$/,

31];

32// 토큰 사본은 보관하지 않고 바로 지운다.

33const

scripts/setup.mjsView file

Lines 1-28javascript

1#!/usr/bin/env node

3// triflux 설치 및 업데이트 설정 스크립트

4// - tfx-route.sh를 ~/.claude/scripts/에 동기화

5// - hud-qos-status.mjs를 ~/.claude/hud/에 동기화

6// - skills/를 ~/.claude/skills/에 동기화

8import { createHash } from "node:crypto";

9import { execFileSync, spawn } from

scripts/mcp-check.mjsView file

•Runtime or CLI code links a write operation to an explicit external AI-agent control path: , config)); } } } for (const mcpjson of scanpluginsmcpjson()) { for (const { name, config } of extractmcpservernames(mcpjson)) { if (!servermap.has(name)) { servermap.set(name, createserverrecord(name, "configured", config)); } } } for (const settingsfile of ["settings.json", "settings.local.json"]) { const data = readjsonsafe(join(claude_dir, settingsfile)); if (!data?.mcpservers) continue; for (const [name, config] of object.entries(data.mcpservers)) { if (typeof name !== "string" || !name.trim()) continue; if (!servermap.has(n

High

External Ai Agent Control Surface Mutation

Runtime or CLI source writes behavior-bearing configuration into a user or project AI-agent control surface.

scripts/mcp-check.mjsView on unpkg

scripts/ensure-codex-hooks.mjsView file

•Manifest-trigger-reachable source links an external AI-agent control path to a behavior-bearing write operation. nction mergehooksstate(content, entries, hookspath) { const managedkeys = new set(entries.map((entry) => entry.key)); if (hooksstateconverged(content, entries, hookspath)) { return content; } return appendstateblocks( stripmanagedstatelines(content, managedkeys, hookspath), entries, ); }

High

Trigger Reachable External Ai Agent Control Surface Mutation

Manifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.

scripts/ensure-codex-hooks.mjsView on unpkg

scripts/lib/codex-recovery.shView file

•path = scripts/lib/codex-recovery.sh kind = build_helper sizeBytes = 3399 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

scripts/lib/codex-recovery.shView on unpkg

hub/team/headless.mjs#virtual:normalized:round1View file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 4

High

Semantic Analysis Limited

A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.

hub/team/headless.mjs#virtual:normalized:round1View on unpkg

hub/team/headless.mjsView file

•matchType = normalized_sha256 matchedPackage = triflux@10.55.1 matchedPath = hub/team/headless.mjs matchedIdentity = npm:dHJpZmx1eA:10.55.1 similarity = 1.000 summary = normalized source hash matched finalized malicious source

High