Skills/PyPI/mcp-server-ssh

mcp-server-ssh@2.0.0

CAUTION· not started

Publisher claims: "SSH MCP server for remote Linux command execution via Model Context Protocol" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher mytsx · publishing for 271 daysInstalls 352Last detonated 5d ago
What would fix thisWatchDispute verdict

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
SSH_PASSWORDConfiguration, not credentials: SSH_HOST, SSH_KEY_FILE, SSH_KEY_PASSPHRASE, SSH_USER
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 SSH_PASSWORD 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 mcp-server-ssh

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 2026-11-09 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 file system command detected; Destructive file system command detected; Hidden zero-width characters 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
File permission modification commandsrc/mcp_server_ssh/server.py:108 · File permission modification command — agent changes file ownership/permissions# Case matters here: chmod/chown spell recursive as an uppercase -R, andFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Destructive file system command detectedsrc/mcp_server_ssh/server.py:80 · Destructive file system command detected# `rm -rf /` and `rm -rf /*`, but not `rm -rf /var/tmp/build` — that one isFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_smoke.py:136 · Destructive command against a filesystem root or device("rm -rf /", True, True),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/mcp_server_ssh/server.py:955 · Process kill command — agent can terminate processesstr, Field(description="Process name or search term; a numeric PID for kill and status.")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedsrc/mcp_server_ssh/server.py:603 · Destructive file system command detected# keeps `rm -rf /; true` from escaping a rule anchored to the end of the input.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_smoke.py:137 · Destructive command against a filesystem root or device("rm -rf /*", True, True),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/mcp_server_ssh/server.py:983 · Process kill command — agent can terminate processes# killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_smoke.py:137 · Destructive file system command detected("rm -rf /*", True, True),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Hidden zero-width characters detectedsrc/mcp_server_ssh/server.py:607 · Hidden zero-width characters detected — may conceal content# `r$()m`, `r${x}m` (x unset) and `r`​`​`m` all invoke rm. They are removed beforeFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Process kill commandsrc/mcp_server_ssh/server.py:957 · Process kill command — agent can terminate processessignal: Annotated[str, Field(description="Signal to send, for the kill action.")] = "TERM",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandsrc/mcp_server_ssh/server.py:651 · File permission modification command — agent changes file ownership/permissionsbecause `chmod -R` is not the same option as `chmod -r`. Each segment of aFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
CRITICAL
Destructive command against a filesystem root or devicesrc/mcp_server_ssh/server.py:80 · Destructive command against a filesystem root or device# `rm -rf /` and `rm -rf /*`, but not `rm -rf /var/tmp/build` — that one isFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandsrc/mcp_server_ssh/server.py:114 · File permission modification command — agent changes file ownership/permissions# `chmod 755 /srv -R` is recursive.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_smoke.py:182 · Destructive command against a filesystem root or device('bash -c "rm -rf /"', True, True),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedsrc/mcp_server_ssh/server.py:72 · Destructive file system command detected# before *and after* the file operands — `rm /tmp/missing -rf /var` deletesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_smoke.py:142 · Destructive file system command detected("rm -rf /var/tmp/build", False, True),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_smoke.py:136 · Destructive file system command detected("rm -rf /", True, True),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/mcp_server_ssh/server.py:1003 · Process kill command — agent can terminate processesresult = await ssh.run(f"kill -{quote(signal)} {target}")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_smoke.py:139 · Destructive command against a filesystem root or device("mkfs.ext4 /dev/sda", True, False),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_smoke.py:138 · Destructive file system command detected("rm -rf /var", True, True),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_smoke.py:175 · Destructive command against a filesystem root or device("rm -rf / && echo ok", True, True),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_smoke.py:168 · Destructive file system command detected("rm /tmp/missing -rf /var", True, True),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandtests/test_smoke.py:165 · File permission modification command — agent changes file ownership/permissions("chmod 755 file", False, False),Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedtests/test_smoke.py:438 · 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
File permission modification commandtests/test_smoke.py:161 · File permission modification command — agent changes file ownership/permissions("chmod -R 755 /var/www", False, True),Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandtests/test_smoke.py:522 · Process kill command — agent can terminate processesassert not any(c.startswith("kill ") for c in host.commands)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_smoke.py:512 · Process kill command — agent can terminate processes"Mon Jan 1 12:00:00 2026 postgres", # what holds the PID by kill timeFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandtests/test_smoke.py:163 · File permission modification command — agent changes file ownership/permissions("chmod --recursive 755 /srv", False, True),Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandtests/test_smoke.py:64 · Process kill command — agent can terminate processesif command.startswith("kill "):Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandtests/test_smoke.py:164 · File permission modification command — agent changes file ownership/permissions("chmod -v -R 755 /srv", False, True),Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandtests/test_smoke.py:162 · File permission modification command — agent changes file ownership/permissions("chown -R user:group /srv", False, True),Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈56 tok
1 file · 16 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 mcp-server-ssh@2.0.0 as of 5d 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. Unclaimed publisher≈ +8 on the totalClaim mytsx: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  4. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  5. Destructive command against a filesystem root or device≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  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 mytsxPropose a patch to the maintainer