sagemath-mcp@0.10.1
CAUTION· not startedPublisher claims: "Model Context Protocol server that provides stateful SageMath computations." 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
- sagemath.org (its own)
- 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 and talks to sagemath.org, its own; 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 2026-11-16 and scored it 71/100 (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; 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
# (lambda f=open: f('/etc/passwd').readline())()Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Both returned the first line of /etc/passwd, through evaluate_sage andFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# f = open; f('/etc/passwd').readline()Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# *and* is absent from the namespace and the allowlist, so `os.system(...)`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# kill that reaches only the worker leaves those orphaned andFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."\u0391\u0392\u0393\u0394\u0395\u0396\u0397\u0398\u0399\u039a\u039b\u039c"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.probe that fails because a computation is wedged tells Kubernetes to killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# os.listdir, os.environ and os.chmod were not -- and the README claimedFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.# kill and is what remains of the old behaviour everywhere else.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."\u039d\u039e\u039f\u03a0\u03a1\u03a3\u03a4\u03a5\u03a6\u03a7\u03a8\u03a9"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."\u03bd\u03be\u03bf\u03c0\u03c1\u03c2\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.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 sagemath-mcp@0.10.1 as of 41 min ago. This is the package itself, not its dependencies.
What would make this Verified
9 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 xbp-europe: 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.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Unicode escape sequence detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.