Skills/PyPI/sandbox-mcp

sandbox-mcp@0.4.0

CAUTION· not started

Publisher claims: "General-purpose Python execution sandbox with FastMCP tools, artifact capture, Manim rendering, and web demo workflows" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher scooter-lacroix · publishing for 248 daysInstalls 80Last 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
MSB_API_KEYConfiguration, not credentials: MSB_SERVER_URL, SANDBOX_ARTIFACT_MAX_AGE, SANDBOX_CLEANUP_INTERVAL, SANDBOX_MAX_ARTIFACTS_MB, SANDBOX_MAX_CACHE_SIZE, SANDBOX_MAX_EXECUTION_TIME, SANDBOX_MAX_MEMORY_MB, SANDBOX_MAX_PROCESSES, SANDBOX_MAX_SESSIONS, SANDBOX_MAX_THREADS, SANDBOX_MCP_DEBUG, SANDBOX_MCP_HOST, SANDBOX_MCP_PORT, VIRTUAL_ENV
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 MSB_API_KEY 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 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 2026-11-16 and scored it 68/100 (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; OS command execution function call detected. 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/core/worktree_manager.py:50 · Python subprocess execution detectedresult = 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/core/security.py:134 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesr'/etc/sudoers', # Sudo configurationFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/sandbox/core/manim_support.py:374 · Python subprocess execution detectedresult = subprocess.run(['manim', '--version'], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/sandbox/core/worktree_isolation.py:160 · 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 detectedrun_sandbox.py:36 · Python subprocess execution detectedsubprocess.run([sys.executable, "-m", "pytest", "tests/", "-v"])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/core/security.py:132 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesr'/etc/passwd', # System usersFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedrun_sandbox.py:26 · Python subprocess execution detectedsubprocess.run([sys.executable, "-m", "sandbox.mcp_sandbox_server"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
OS command execution function call detectedplayground.py:138 · OS command execution function call detectedos.system('clear' if os.name == 'posix' else 'cls')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/sandbox/core/security.py:141 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesr'~/.ssh/', # SSH keysFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandsrc/sandbox/core/security.py:90 · Process kill command — agent can terminate processesr'pkill\s+', # Process killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedenhanced_repl.py:148 · 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 detectedplayground.py:280 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Destructive file system command detectedsrc/sandbox/sdk/command.py:134 · Destructive file system command detected"del /f",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedrun_sandbox.py:21 · Python subprocess execution detectedsubprocess.run([sys.executable, "playground.py"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/sandbox/core/worktree_isolation.py:210 · 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 commandsrc/sandbox/core/security.py:91 · Process kill command — agent can terminate processesr'kill\s+-9', # Force killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/sandbox/core/manim_support.py:278 · 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 detectedrun_sandbox.py:31 · Python subprocess execution detectedsubprocess.run([sys.executable, "-m", "sandbox.mcp_sandbox_server_stdio"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/sandbox/core/manim_support.py:385 · Python subprocess execution detectedresult = subprocess.run(['manim', 'cfg', 'show'], capture_output=True, text=True)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/core/security.py:133 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesr'/etc/shadow', # System passwordsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
OS command execution function call detectedsrc/sandbox/server/help_text.py:305 · OS command execution function call detected"Use shell_execute() instead of os.system() for safety",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/sandbox/core/worktree_manager.py:129 · 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/server/execution_helpers.py:702 · Python subprocess execution detectedprocess = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Context shift attemptENHANCED_FEATURES.md:311 · Context shift attempt — trying to change operational mode · informational: not an instruction fileEnable debug mode for detailed logging:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/sandbox/sdk/command.py:151 · 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/server/package_helpers.py:240 · Python subprocess execution detectedlist_result = 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/server/package_helpers.py:128 · Python subprocess execution detectedinstall_result = 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/core/worktree_manager.py:160 · 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/core/worktree_manager.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
MEDIUM
Python subprocess execution detectedsrc/sandbox/core/worktree_manager.py:169 · Python subprocess execution detectedbranch_result = 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/server/shell_helpers.py:98 · Python subprocess execution detectedprocess = 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/server/manim_helpers.py:96 · Python subprocess execution detectedprocess = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandsrc/sandbox/sdk/command.py:131 · File permission modification command — agent changes file ownership/permissions"chmod 777",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedsrc/sandbox/server/web_export_docker.py:98 · 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/server/web_export_docker.py:134 · 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/sdk/worktree_sandbox.py:364 · 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/server/web_export_docker.py:52 · 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
≈1,334 tok
2 files · 81 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-mcp@0.4.0 as of 40 min ago. This is the package itself, not its dependencies.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Unclaimed publisher≈ +8 on the totalClaim scooter-lacroix: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  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. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  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 scooter-lacroixPropose a patch to the maintainer