Loading npm security reports…

@tyroneross/coding-debugger@1.9.0: AI-agent control-surface risk | LPM Firewall

registry / @tyroneross/coding-debugger / 1.9.0

@tyroneross/coding-debugger@1.9.0

Coding Debugger for Claude Code and Codex: debugging memory, verdict-first retrieval, root-cause workflows, context compression, and parallel assessment.

AI Security Review

scanned 1mo ago · by lpm-firewall-ai

LPM flags this version as an AI-agent control-surface risk. Installing the package automatically mutates the consumer project's Claude configuration and instructions. It adds a Stop hook that launches another package through npx.

Static reason

High-risk behavior combination matched malicious policy.

Trigger

npm postinstall during package installation

Impact

Changes agent behavior, injects commands and instructions, and executes an external package whenever a Claude session ends.

Mechanism

Automatic Claude control-surface writes and persistent npx session hook

Policy narrative

On npm installation, postinstall targets the consumer project and creates Claude memory data, command files, hooks, and CLAUDE.md content. The installed Stop hook runs npx @tyroneross/claude-code-debugger automatically at each session end. The package name differs from the package being fetched and executed, while bundled update material reinforces installing that external latest release and rerunning setup.

AI rationale

This is an unconsented install-time mutation of a foreign AI-agent control surface, with persistent automatic execution of another registry package. The absence of observed secret theft does not remove the concrete control-hijack chain.

Evidence

package.jsondist/src/setup/auto-setup.jsdist/src/setup/create-slash-commands.jsdist/src/setup/inject-claude-md.jsdist/src/setup/configure-hooks.jsdist/cli/index.jscommands/update.md.claude/memory/.claude/commands/

Source & flagged code

7 flagged · loading source

package.jsonView file

•scripts.postinstall = node dist/src/setup/auto-setup.js || true

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg

•scripts.postinstall = node dist/src/setup/auto-setup.js || true

Medium

Ambiguous Install Lifecycle Script

Install-time lifecycle script is not statically allowlisted and needs review.

package.jsonView on unpkg

dist/cli/index.jsView file

270.action(async (options) => { L271: const { exec } = await Promise.resolve().then(() => __importStar(require('child_process'))); L272: console.log('\n💬 Claude Code Debugger - Feedback');

High

Child Process

Package source references child process execution.

dist/cli/index.jsView on unpkg · L270

•Runtime or CLI code links a write operation to an explicit external AI-agent control path: onst url = `https://github.com/tyroneross/claude-code-debugger/issues/new?labels=${labels}&title=${title}&body=${body}`; console.log(` opening github to submit ${issuetype}...\n`); const opencommand = process.platform === 'darwin' ? 'open' : process.platform === 'win32' ? 'start' : 'xdg-open'; exec(`${opencommand} "${url}"`, (error) => { if (error) { console.log(' could not open browser automatically.'); console.log(` please visit: ${url}\n`); } else { console.log(' ✅ browser opened! create your issue on github.\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.

dist/cli/index.jsView on unpkg

497// Global install: update globally L498: execSync('npm install -g @tyroneross/claude-code-debugger@latest', { L499: stdio: 'inherit'

High

Runtime Package Install

Package source invokes a package manager install command at runtime.

dist/cli/index.jsView on unpkg · L497

dist/src/setup/auto-setup.jsView file

9* What it does: L10: * 1. Creates memory directories (.claude/memory/) L11: * 2. Installs slash commands (/debugger, /debugger-detail, etc.) L12: * 3. Configures session hooks (auto-mine on session end) L13: * 4. Adds Debugging Memory section to CLAUDE.md L14: */ ... L71: return true; L72: if (process.env.CLAUDE_MEMORY_SKIP_SETUP === 'true') L73: return true; ... L101: // 1. Create memory directories L102: const memoryPath = path.join(projectRoot, '.claude', 'memory'); L103: fs.mkdirSync(path.join(memoryPath, 'incidents'), { recursive: true });

Critical

Ai Agent Control Hijack

Source creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.

dist/src/setup/auto-setup.jsView on unpkg · L9

dist/package.jsonView file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 2

High

Semantic Analysis Limited

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

dist/package.jsonView on unpkg

Source & flagged code

7 flagged

package.jsonView file

Lines 14-54json

14 "bin": {

15 "coding-debugger": "dist/cli/index.js",

16 "claude-code-debugger": "dist/cli/index.js"

17 },

18 "files": [

19 "dist",

20 "commands",

21 "skills",

22 "hooks",

23 "agents",

24 ".claude-plugin",

25 ".codex-plugin",

26 ".mcp.json",

27 "README.md",

28 "LICENSE"

29 ],

30 "scripts": {

31 "build": "tsc",

32 "watch": "tsc --watch",

33 "prepublishOnly": "npm run build",

34 "postinstall": "node dist/src/setup/auto-setup.js || true",

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg · L34

Medium

Ambiguous Install Lifecycle Script

Install-time lifecycle script is not statically allowlisted and needs review.

package.jsonView on unpkg · L34

35 "test": "node test-v1.4.0-e2e.js && node test-v1.5.0-e2e.js",

36 "benchmark": "node benchmark-scoring.js",

37 "mcp": "node dist/src/mcp/server.js",

38 "clean": "rm -rf dist"

39 },

40 "keywords": [

41 "debugging",

42 "memory",

43 "coding-debugger",

44 "claude-code",

45 "codex",

46 "agent-tools",

47 "incident-tracking",

48 "pattern-recognition",

49 "developer-tools",

50 "opentelemetry",

51 "traces",

52 "parallel-assessment",

53 "sentry",

54 "langchain"

dist/cli/index.jsView file

Lines 250-290javascript

250 console.log(' --incomplete Review incomplete incidents interactively');

251 console.log(' --extract-patterns Extract patterns from similar incidents');

252 console.log(' --cleanup Clean up old sessions and low-quality incidents\n');

253 console.log('Examples:\n

dist/src/setup/auto-setup.jsView file

Lines 1-29javascript

1#!/usr/bin/env node

2"use strict";

3/**

4 * Auto-Setup Script

5 *

6 * Runs automatically after npm install to set up debugging memory.

7 * Zero user action required — just install and it works.

8 *

9 * What it does:

10 * 1. Creates memory directories (.claude/memory/)

11

dist/package.jsonView file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 2

High

Semantic Analysis Limited

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

dist/package.jsonView on unpkg