Skills/PyPI/remote-sandbox-mcp

remote-sandbox-mcp@0.7.6

CAUTION· not started

Publisher claims: "MCP server for SSH-based remote sandboxes: multi-server management, persistent sessions, background tmux tasks, and GPU/CPU/memory resource monitoring" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher debinxiangquantum · publishing for 77 daysInstalls 140Last detonated 51 min ago

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
REMOTE_PASSWORDConfiguration, not credentials: REMOTE_HOST, REMOTE_KEY_FILE, REMOTE_KEY_PASSPHRASE, REMOTE_PORT, REMOTE_SANDBOX_EXPOSE_ADVANCED_TOOLS, REMOTE_SANDBOX_LIST, REMOTE_SANDBOX_MCP_HOME, REMOTE_USER, XDG_STATE_HOME
Where it talks to
no vendor host named in the code
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard. It asks for REMOTE_PASSWORD and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --net declared -- uvx remote-sandbox-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-15 and scored it 72/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Privileged sudo command. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedremote_sandbox_mcp/watchdog_daemon.py:536 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandremote_sandbox_mcp/server.py:1573 · Process kill command — agent can terminate processes"Use a different session_name or kill the existing session first with: "Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsremote_sandbox_mcp/server.py:125 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileskey_file: str = "" # Path to private key file, e.g. "~/.ssh/id_ed25519"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsremote_sandbox_mcp/server.py:167 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files'[{"name":"gpu1","host":"10.0.0.1","user":"ubuntu","key_file":"~/.ssh/id_ed25519"}]'Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedremote_sandbox_mcp/watchdog_daemon.py:453 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandremote_sandbox_mcp/server.py:1580 · Privileged sudo command — agent may execute with elevated privileges"or: sudo yum install tmux (CentOS/RHEL)"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedremote_sandbox_mcp/server.py:2647 · Python subprocess execution detectedreturn subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandremote_sandbox_mcp/server.py:703 · File permission modification command — agent changes file ownership/permissionsf"chmod 700 {shlex.quote(script_path)}",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
References a credential file in the home directoryremote_sandbox_mcp/server.py:167 · References a credential file in the home directory'[{"name":"gpu1","host":"10.0.0.1","user":"ubuntu","key_file":"~/.ssh/id_ed25519"}]'Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
References a credential file in the home directoryremote_sandbox_mcp/server.py:125 · References a credential file in the home directorykey_file: str = "" # Path to private key file, e.g. "~/.ssh/id_ed25519"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Privileged sudo commandremote_sandbox_mcp/server.py:1579 · Privileged sudo command — agent may execute with elevated privileges"Install it with: sudo apt-get install tmux (Debian/Ubuntu) "Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandremote_sandbox_mcp/watchdog_daemon.py:364 · File permission modification command — agent changes file ownership/permissionsf"chmod 700 {shlex.quote(script_path)}",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedremote_sandbox_mcp/watchdog_service.py:121 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedremote_sandbox_mcp/watchdog_service.py:103 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈1,840 tok
1 file · 15 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim debinxiangquantum: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim debinxiangquantumPropose a patch to the maintainer