Skills/PyPI/sandbox-env-mcp

sandbox-env-mcp@0.3.1

CAUTION· not started

Publisher claims: "Sandbox Environment Manager MCP server" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher sandbox-mcp-contributors · publishing for 120 daysInstalls 180Last detonated 1 h 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
SANDBOX_MCP_SERVER_AUTH_TOKENS_FILEConfiguration, not credentials: DOCKER_CERT_PATH, SANDBOX_MCP_CONFIG, SANDBOX_MCP_SERVER_HOST, SANDBOX_MCP_SERVER_PORT
Where it talks to
no vendor host named in the codeAlso gnu.org — not the publisher's domain; check what for before connecting.
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, and read the third-party hosts first. The code names gnu.org as well as its own vendor. The guard injects SANDBOX_MCP_SERVER_AUTH_TOKENS_FILE only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx sandbox-env-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 2026-11-16 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; References a credential file in the home directory. 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 detectedsrc/sandbox_mcp/encoding_utils.py:146 · Python subprocess execution detectedproc = subprocess.run(cmd, capture_output=True, timeout=connect_timeout)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/sandbox_mcp/backends/ssh_backend.py:291 · 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 detectedsrc/sandbox_mcp/shell_session.py:68 · Python subprocess execution detectedself._process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/sandbox_mcp/backends/ssh_backend.py:333 · Python subprocess execution detectedcheck = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/sandbox_mcp/sandbox_env.py:660 · Process kill command — agent can terminate processes"long-running command, kill the shell "Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandsrc/sandbox_mcp/server.py:846 · File permission modification command — agent changes file ownership/permissions" chmod 600 it. Or set:\n"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandtests/test_auth.py:68 · File permission modification command — agent changes file ownership/permissions# chmod 644Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedsrc/sandbox_mcp/backends/ssh_backend.py:404 · Python subprocess execution detectedcheck = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/sandbox_mcp/safety.py:33 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files``cat /etc/shadow`` and read it. The advisory exists to give the modelFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/test_lint.py:62 · 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 detectedsrc/sandbox_mcp/backends/ssh_backend.py:166 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True, timeout=15)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/sandbox_mcp/backends/docker_backend.py:261 · Process kill command — agent can terminate processes# Private form used by exec_inspect / kill paths; public alias soFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/sandbox_mcp/safety.py:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesis the same: ``/etc/shadow`` and friends, ``~/.ssh``, ``~/.aws``, ``.env``Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_docker_backend.py:462 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdockerfile="/etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
References a credential file in the home directorysrc/sandbox_mcp/backends/docker_backend.py:406 · References a credential file in the home directory``~/.docker/config.json`` contexts.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Python subprocess execution detectedsrc/sandbox_mcp/backends/ssh_backend.py:98 · Python subprocess execution detectedcheck = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_safety.py:31 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"/etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_safety.py:32 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"/etc/sudoers",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
References a credential file in the home directorytests/test_safety.py:155 · References a credential file in the home directoryresult = check_path_safety("~/.ssh/id_rsa")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Access to sensitive file pathstests/test_safety.py:30 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"/etc/shadow",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Host or command assembled from base64 fragmentstests/test_shell_provider.py:97 · Host or command assembled from base64 fragmentsassert "base64 -d" in cmdFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Python subprocess execution detectedtests/test_lint.py:82 · 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
Access to sensitive file pathstests/test_safety.py:43 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""``../etc/shadow`` must resolve and trigger the advisory."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_safety.py:58 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesthe advisory fires. Simulate by writing a real file under /etc/shadowFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈47 tok
1 file · 53 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

No advisories in OSV for sandbox-env-mcp@0.3.1 as of 51 min ago. This is the package itself, not its dependencies.

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 sandbox-mcp-contributors: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Obfuscated code≈ +5 on the totalRemove base64-assembled strings, eval of decoded text and minified blobs. Reviewers and scanners both treat unreadable code as hostile.
  3. 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.
  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 sandbox-mcp-contributorsPropose a patch to the maintainer