sandbox-mcp@0.4.0
CAUTION· not startedPublisher 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.
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.
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 deviationsStatic findings
result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r'/etc/sudoers', # Sudo configurationFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = 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.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([sys.executable, "-m", "pytest", "tests/", "-v"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r'/etc/passwd', # System usersFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.subprocess.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.os.system('clear' if os.name == 'posix' else 'cls')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.r'~/.ssh/', # SSH keysFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.r'pkill\s+', # Process killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run([Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."del /f",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.subprocess.run([sys.executable, "playground.py"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r'kill\s+-9', # Force killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.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.result = 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.r'/etc/shadow', # System passwordsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."Use shell_execute() instead of os.system() for safety",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Enable debug mode for detailed logging:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.list_result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.install_result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.branch_result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.process = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.process = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."chmod 777",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
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 51 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%- OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- 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.
- 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.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.