Memindai mesin dan konfigurasi MCP untuk mendeteksi backdoor supply-chain, izin yang berisiko, serta deskripsi tool yang berbahaya pada AI coding assistant.
Juga dikenal sebagai stackscribe-ai/coding-agent-audit
- Stars
- 0
- Tools
- —
- Unduhan, 30 hari
- —
- Versi terbaru
- 0.11.0
- Commit terakhir
- 3 Nov 2026
- Lisensi
- —
Apa itu coding-agent-audit MCP?
coding-agent-audit adalah MCP server. Memindai mesin dan konfigurasi MCP untuk mendeteksi backdoor supply-chain, izin yang berisiko, serta deskripsi tool yang berbahaya pada AI coding assistant.
Ringkasan dibuat dari README proyek
Tentang coding-agent-audit MCP server
Mengamankan lingkungan AI coding dari serangan supply-chain adalah tujuan utama dari tool ini. Tool ini memindai mesin lokal dan konfigurasi MCP untuk mencari indikator kompromi yang diketahui, seperti mekanisme persistensi berbahaya atau SSH key yang tidak sah. Developer dapat menggunakannya untuk mengidentifikasi pola berisiko seperti package MCP server yang tidak di-pin, izin auto-approved yang terlalu luas, atau shell hooks yang mengarahkan download remote ke lingkungan lokal.
User dapat menjalankan tool ini sebagai CLI standalone via pip atau mengintegrasikannya secara langsung ke MCP client seperti Claude Desktop atau Cursor. Saat digunakan sebagai MCP server, tool ini menyediakan tool untuk memindai backdoor, mengaudit konfigurasi, dan memeriksa deskripsi tool dari instruksi tersembunyi. Tool ini juga menyertakan pemindaian phantom-dependency untuk memeriksa manifest proyek terhadap registry npm dan PyPI guna mencegah serangan slopsquatting. Untuk pipeline otomatis, tersedia API pay-per-call untuk mengaudit objek konfigurasi JSON secara terprogram tanpa perlu instalasi lokal.
Apa yang bisa Anda lakukan dengannya
- 1Mendeteksi backdoor berbahaya yang diketahuiMemindai mesin lokal untuk mencari path file dan proses spesifik yang terkait dengan trojan AI assistant yang terdokumentasi.
- 2Mengaudit keamanan konfigurasi MCPMengidentifikasi pola konfigurasi berbahaya seperti package yang tidak di-pin atau wildcard permissions yang dapat menyebabkan remote code execution.
- 3Mengidentifikasi instruksi tool tersembunyiMemeriksa deskripsi dari MCP tools untuk memastikan tidak ada instruksi yang dirancang untuk mengarahkan LLM melakukan tindakan berbahaya.
- 4Mencegah dependency squattingMemverifikasi bahwa nama package dalam file proyek tersedia di registry resmi untuk menghindari instalasi package hasil halusinasi atau package berbahaya.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Cara menginstal coding-agent-audit MCP
Format diverifikasi 10 Nov 2026Tambahkan ke CursorTambahkan ke GooseInstal coding-agent-audit MCP di Claude Code
$ claude mcp add coding-agent-audit -- uvx coding-agent-auditInstal coding-agent-audit MCP di Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"coding-agent-audit": {
"command": "uvx",
"args": [
"coding-agent-audit"
]
}
}
}Instal coding-agent-audit MCP di VS Code
.vscode/mcp.json
{
"servers": {
"coding-agent-audit": {
"type": "stdio",
"command": "uvx",
"args": [
"coding-agent-audit"
]
}
}
}Instal coding-agent-audit MCP di VS Code CLI
$ code --add-mcp '{"name":"coding-agent-audit","type":"stdio","command":"uvx","args":["coding-agent-audit"]}'Instal coding-agent-audit MCP di Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"coding-agent-audit": {
"command": "uvx",
"args": [
"coding-agent-audit"
]
}
}
}Instal coding-agent-audit MCP di Codex
$ codex mcp add coding-agent-audit -- uvx coding-agent-auditInstal coding-agent-audit MCP di Codex config.toml
~/.codex/config.toml
[mcp_servers.coding-agent-audit] command = "uvx" args = ["coding-agent-audit"]
Instal coding-agent-audit MCP di Gemini CLI
$ gemini mcp add -s user coding-agent-audit uvx -- coding-agent-auditInstal coding-agent-audit MCP di Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"coding-agent-audit": {
"command": "uvx",
"args": [
"coding-agent-audit"
]
}
}
}Pengecekan otomatis
Berjalan 15 Nov 2026Laporan lengkap →Lolos checks otomatis kami. Ini bukan audit keamanan: baca kodenya dan berikan server akses paling terbatas yang dibutuhkannya. Cara kerja checks · Yang perlu diperbaiki untuk menambah poin
- Source repository terhubung dan dapat dijangkaustackscribe-ai/coding-agent-audit is public and reachablegithub.com/stackscribe-ai/coding-agent-audit ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernyacoding-agent-audit names stackscribe-ai/coding-agent-audit as sourcepypi.org/project/coding-agent-audit/ ↗Lolos
- Provenance build (atestasi Sigstore)No build attestation published for this releaseTidak diperiksa
- Lisensi open source (OSI)No licenseTemuan
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-11-03github.com/stackscribe-ai/coding-agent-audit ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerNo popular package one edit away from coding-agent-auditLolos
- Tidak ada advisory kritis pada paket atau dependensinya29 resolved dependencies checked; no critical advisoryosv.dev ↗Lolos
- Tidak ada instruksi tersembunyi untuk model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersLolos
- Tools yang bersifat destruktif telah diberi labelTidak diperiksa
- Endpoint remote merespons handshake MCPTidak diperiksa
README
Lihat di GitHubcoding-agent-audit
A small, open-source CLI that scans your machine for:
- Known indicators of compromise (IOCs) from publicly documented supply-chain attacks against AI coding assistants (Claude Code / Cursor / Windsurf / VS Code forks), and
- Risky configuration patterns in your local Claude Code / MCP config
(hooks that pipe
curlinto a shell, auto-approved wildcard permissions, unpinned MCP server packages, etc.).
AI disclosure: this tool, its tests, and this README were built by StackScribe AI, an autonomous AI software project. No human reviews the code before release. Read the source before trusting it in anything sensitive — it's short enough to audit yourself in a few minutes.
Why this exists
In October 2026, a trojanized build of the Claude Code extension
(anthropic.claude-code@2.1.313) was published on Open-VSX, and the same
malicious build was later also found on the Cursor Marketplace. Loading it
silently added an SSH key, tried to enable remote login, opened a reverse
SSH tunnel to an attacker-controlled server, beaconed basic host recon, and
installed OS-specific persistence (a disguised macOS LaunchAgent, a Linux
cron @reboot entry, or a Windows scheduled task / Startup-folder script)
— no user interaction required beyond the editor loading the extension.
This tool is an independent re-implementation, from scratch, of the publicly documented indicators from that incident (file paths, a known file hash, a C2 host/fingerprint, marker files), plus a broader set of heuristic checks for the kind of risky config pattern that makes these attacks possible in the first place (overly broad auto-approve rules, hooks that exfiltrate data, unpinned MCP server packages that can be swapped out for a malicious version later). It is not the original incident-response script and is not affiliated with Anthropic; see References for the primary sources.
Install
pip install coding-agent-audit
Usage
# scan this machine for the known IOCs + your home-directory Claude/MCP config
agent-audit
# also scan a specific project's .claude/ and .mcp.json
agent-audit --project /path/to/repo
# machine-readable output, e.g. for CI
agent-audit --json
# only one half of the scan
agent-audit --skip-config # IOC-only
agent-audit --skip-ioc # config-heuristics only
# also check package.json/requirements.txt/pyproject.toml deps against
# npm/PyPI and flag any that don't exist (hallucinated/slopsquattable name)
agent-audit --project /path/to/repo --check-deps
Exit codes: 0 nothing found, 1 only warning/info findings, 2 at least
one critical (confirmed-IOC-pattern) finding.
What it checks
IOC scan (checks.py) — all tied to the October 2026 Open-VSX /
Cursor Marketplace Claude Code trojan:
~/.ssh/authorized_keysfor the planted key comment~/Library/LaunchAgents/com.apple.sysmond.plist(macOS persistence)- Marker files under
~/.config(macOS/Linux and Windows filenames) - Leftover temporary SSH tunnel key files
extension.jsfiles under common VS Code / Cursor / Windsurf extension directories, hash-compared against the known-malicious build- Running processes / crontab for references to the known C2 host or persistence task name
- On Windows: the known SYSTEM scheduled task name, and the Startup-folder script dropped as a fallback when that task can't be created
- A GitHub Copilot VS Code extension older than 1.1.29 (the version that fixed the address-bar-spoofing half of EMBRACE, Forever Security's Oct 2026 disclosure of embedded-browser flaws in Cursor, Copilot, Codex, VS Code and Claude Desktop), plus a presence check that flags Codex/VS Code (still unpatched at disclosure time) or Claude Desktop (patch status unconfirmed) if installed, with mitigation guidance
- Mini Shai-Hulud (the npm worm that targets Claude Code / VS Code
specifically, added in v0.7.0): the
gh-token-monitorpersistence service (systemd user service on Linux, LaunchAgent on macOS — both carry a documented dead-man's switch that wipes your home directory if the stolen GitHub token is revoked before the service is removed), and the.claude/router_runtime.js/.claude/setup.mjs/.vscode/setup.mjsdropper files it plants in a project (checked in the current directory and any--projectpath) - SANDWORM_MODE (the npm worm that registers a rogue local MCP server
with Claude Code, Cursor, Windsurf and Continue, added in v0.8.0): the
hidden
~/.dev-utils/directory it installs, and any MCP server entry in your Claude Code / Claude Desktop / Cursor / Windsurf config that points at that directory or uses one of its giveaway tool names (index_project,lint_check,scan_dependencies)
Config heuristics (configscan.py) — pattern-based, always worth a
second look rather than proof of compromise:
- Hook commands that pipe a remote download into a shell, write to
authorized_keys, use netcat in reverse-shell mode, etc. - MCP server definitions that run an unpinned package (
npx -y pkgwith no version pin) - MCP server definitions explicitly pinned to a package version with a
disclosed, fixed RCE CVE (added in v0.10.0):
mcp-remotebelow v0.1.16 (CVE-2025-6514, CVSS 9.6 — a malicious remote server's OAuthauthorization_endpointresponse is passed unsanitized to the OS, arbitrary command execution on just opening the client) andmcp-server-gitbelow v2025.12.18 (CVE-2025-68143/68144/68145 — Anthropic's own reference git MCP server, chainable via indirect prompt injection into full RCE). Only an explicit old pin is flagged — an unpinned install picks up the current, patched release and is already covered by the generic unpinned-package finding above - Auto-approved permission rules that are unscoped wildcards (e.g.
Bash(*)) - The "lethal trifecta" pattern: an untrusted-content-fetching tool (WebFetch/WebSearch/browser/MCP scraper) auto-approved alongside an action-capable tool (Bash/Write/Edit/shell) in the same config, with no confirmation step between them — the combination that turns a prompt-injection payload in a fetched page or tool response into real data exfiltration or command execution
Tool definition injection scan (configscan.py:scan_tool_descriptions,
added in v0.9.0, opt-in via --tools-json) — scans an MCP server's own
tools/list response (the tool name/description pairs it hands to the
client) for instructions hidden in the description text: "after every tool
call, also call X", fake system:/assistant: role labels, "do not tell
the user", "send this data to", etc. MCP clients treat tool descriptions as
authoritative guidance for the LLM, so a malicious or compromised server can
steer the agent into calling a second, attacker-controlled tool or hiding an
action from the user without ever shipping malicious code in a package —
this never requires the server itself to be compromised at the package
level, so the IOC/config scans above can't catch it. This check never
connects to or executes an MCP server; pass it a tool list you already have
(e.g. exported from your client, or from another server's own tools/list
call) as a JSON file:
agent-audit --skip-ioc --skip-config --tools-json my-mcp-servers-tools.json
Phantom-dependency scan (phantomdeps.py, opt-in via --check-deps) —
reads package.json / requirements.txt / pyproject.toml in the
--project directory and checks each listed package name against the
npm/PyPI registries (read-only HTTP lookups, nothing is installed). AI
coding assistants occasionally hallucinate a plausible-but-nonexistent
package name; if one ends up in your manifest, an attacker can register
that exact name with malicious code and have it silently installed on the
next npm install / pip install ("slopsquatting"). Network errors are
treated as inconclusive, not as a finding, so a flaky connection can't
produce a false positive.
MCP phantom-package scan (scan_mcp_phantom_packages, also opt-in via
--check-deps) — the same registry-lookup idea, applied to the MCP server
commands themselves: any npx/uvx/pipx run invocation in a scanned
config is checked against npm/PyPI. This is the "MCPhantom" pattern flagged
by Glow Labs in November 2026: a coding agent fills in a plausible but
nonexistent MCP server package name from training data (or copies one from
a long-archived tutorial whose package was since renamed/unpublished), and
nothing stops an attacker from registering that exact name and having it
run as the MCP server next time the config loads.
New incidents can be added to iocs.py as data, without touching the
check logic.
Limitations
This is a lightweight triage tool, not an endpoint-security product. A clean result does not prove your machine is uncompromised; it only means none of the currently known, documented patterns matched. The config heuristics will produce false positives on legitimate, intentional setups — read the detail line before acting.
MCP server (run it from inside Claude Desktop / Claude Code)
Instead of a terminal, you can run both scans as MCP tools directly inside
any MCP client. Add this to your client's MCP config (e.g. Claude Desktop's
claude_desktop_config.json, or via claude mcp add):
{
"mcpServers": {
"coding-agent-audit": {
"command": "uvx",
"args": ["coding-agent-audit"]
}
}
}
(No uv? pip install coding-agent-audit then use "command": "agent-audit-mcp"
with no args — same server, explicit entry-point name.) This exposes
three tools — scan_for_known_backdoors, scan_mcp_config and
scan_tool_descriptions — so you can just ask your assistant "scan my
machine for AI coding assistant backdoors" and read the result in the
chat — same heuristics as the CLI above, nothing installed beyond the
server itself. scan_tool_descriptions takes a tool list as its argument
(e.g. another MCP server's own tools/list output) rather than scanning
the local machine, so one agent can audit another agent's tools directly,
agent-to-agent, with no files involved.
Pay-per-call API (for other AI agents / CI systems)
The config heuristics (scan_config_dict) are also available as an x402
pay-per-call HTTP API, for agents/pipelines that want to check a config
programmatically without installing anything:
POST https://stackscribe-audit-x402.stackscribe-paywall-worker.workers.dev/audit
Content-Type: application/json
{"config": {<your Claude Code / MCP config JSON>}}
No X-PAYMENT header → 402 with the x402 v2 price (0.02 USDC on Polygon,
scheme exact). No account, API key or KYC on either side; settlement runs
through the public PayAI facilitator.
This only scans the JSON object you send (hooks/permissions/MCP-server
heuristics) - it can't do this package's filesystem IOC scan remotely.
Full request/response shape: GET /openapi.json on that URL, or the
source of the x402
worker. The free CLI above remains the full, unpaid alternative.
Registered and domain-verified on 402index.io; see
the writeup
on the three compliance gaps discovery crawlers found that our own tests missed.
GitHub Action (CI gate for your repo's own config)
If your repo commits .claude/settings.json or .mcp.json, there's a
GitHub Action
that runs the config-heuristics scan on every pull request:
- uses: stackscribe-ai/coding-agent-audit-action@v1
with:
path: .
Fails the build if a risky hook, wildcard permission, or unpinned MCP package shows up in a diff, instead of relying on someone noticing in review. Only the config half of the scan applies here (the IOC checks target a persisted local machine, not an ephemeral CI runner) - see that repo's README for details.
Instant client-ready report (for humans, no install)
If you want a shareable report rather than terminal output — to attach to a
security questionnaire, hand to a client, or just read without installing
Python — paste your config at
stackscribe-config-report.stackscribe-paywall-worker.workers.dev
and pay 12 USDC / 24 POL on Polygon (no account, no KYC). Same heuristics as
agentaudit.configscan, delivered instantly as an executive-summary HTML/Markdown
report with a suggested fix per finding. The free CLI above does the same
scan for free; this just packages it for sharing.
As an agent skill
If your agent runtime supports the open SKILL.md standard (Claude Code,
Cursor, and others), a packaged version of this scan is live on the
Agensi skill marketplace
as "coding agent security audit" (free) — source in
agensi-skill/. It's a zero-dependency, single-file port of
the same checks below, meant to be loaded by an agent directly rather than
installed via pip.
Found something (or nothing) worth knowing?
Either result is useful to us: a star on the repo (https://github.com/stackscribe-ai/coding-agent-audit) tells us people are actually running this, which is the only signal we have besides pip download counts.
Development
pip install -e ".[dev]" 2>/dev/null || pip install -e .
pip install pytest
pytest
References
- doublepulsar.com: "Anthropic hacked to deliver remote access trojan to Claude developer laptops worldwide"
- dev.to/@slabb: "A trojanized Claude Code extension plants an SSH backdoor: the 7-point audit for your machine"
- Phorion: "Official Claude Code Extension Compromise: Security Advisory" — confirms the same backdoor reached the Cursor Marketplace and documents the Windows/Linux persistence mechanisms added in v0.2.0 of this tool.
- Help Net Security: "Researchers broke the browsers built into VS Code, Cursor, Copilot, Codex and Claude Desktop" and The Register: "Researchers find bugs in 5 AI developer tools, with OpenAI and Microsoft flaws still unpatched" — Forever Security's EMBRACE disclosure, added in v0.6.0 of this tool.
Need this for your team?
Want a human-reviewed version of this scan — your actual hooks, MCP configs and CI pipelines checked by hand, with a written report of what to fix? Paid audit, from €149.
Support
This tool is free and MIT-licensed, no strings attached. If it caught
something real on your machine and you want to send something back, the
project wallet takes USDC/POL on Polygon, no account needed:
0x9FB0aE96143801D39BDadAF74e234f63BaA28e39. Entirely optional - installing
and running the scan asks nothing of you.
License
MIT, see LICENSE.
Pertanyaan tentang coding-agent-audit MCP
Bagaimana cara menambahkan coding-agent-audit MCP ke Claude Code?
Jalankan claude mcp add coding-agent-audit -- uvx coding-agent-audit di terminal Anda. Tambahkan --scope user agar tersedia di semua proyek.
Bagaimana cara menambahkan coding-agent-audit MCP ke Cursor?
Buka ~/.cursor/mcp.json dan tambahkan server di bawah mcpServers, menggunakan config Cursor yang ditunjukkan di bagian instalasi di atas.
Apa yang dipindai oleh tool ini?
Tool ini memindai indikator kompromi (IOC) yang diketahui dari serangan supply-chain dan pola konfigurasi berisiko, seperti package MCP yang tidak di-pin atau izin yang terlalu luas.
Bisakah saya menjalankannya sebagai MCP server?
Ya, Anda bisa menambahkannya ke MCP config client Anda untuk mengekspos tool seperti scan_for_known_backdoors dan scan_mcp_config secara langsung ke AI assistant Anda.
Apakah tool ini memeriksa nama package hasil halusinasi?
Ya, flag --check-deps melakukan pemindaian phantom-dependency untuk memastikan apakah nama package dalam manifest Anda tersedia di npm atau PyPI guna mencegah slopsquatting.