secure-cluster-mcp@1.0.0
CAUTION· not startedPublisher claims: "MCP server for SLURM cluster interactions enabling end-to-end AI-assisted coding 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
- no credential variables read in the code
- 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 under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
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 2026-11-18 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: Destructive command against a filesystem root or device; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
"rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Load settings at module level — fail fast if .env missingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_file=".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."rm -r /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."chmod -R 777 /",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts."rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.**Cluster details (from `.env`):**Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.{"image": "containers/ml.sif", "command": "python -c 'import os; os.system(\"rm -rf ~\")'"},Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."curl|bash",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."rm -r /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."curl|sh",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.## `.env` config (redacted)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.validate_remote_path("../../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = await client.call_tool("run_remote_command", {"command": "rm -rf /"})Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.download_file("results/output.csv", "/home/user/output.csv")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.result = await client.call_tool("submit_job", {"script_path": "/etc/passwd"})Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = ssh.exec_command("rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.validate_remote_path("/home/testuser/project/../../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.ssh.upload_file(str(temp_local_file), "/etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert "rm -rf /" in result.stdoutFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."chmod 777 /",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.assert "rm -rf /" in result.stdoutFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = ssh.exec_command("rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = await client.call_tool("run_remote_command", {"command": "rm -rf /"})Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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 secure-cluster-mcp@1.0.0 as of 21 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%- Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Unclaimed publisher≈ +8 on the totalClaim floriansp2000: 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.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- OS command execution function call detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.