Is libtmux-mcp@0.1.0a22 safe to install?

libtmux-mcp@0.1.0a22

CAUTION

Publisher claims: "MCP server for tmux, powered by libtmux" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher tmux-python · joined 0 days agoInstalls 289Last detonated 2 h ago

What would fix this Watch Dispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-06 and scored it 58/100 (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; Collapsed <details> block carrying instructions; Destructive file system command 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

0.1sprocessexec /usr/bin/date

0.1sprocessexec /usr/bin/timeout

0.1sprocessexec .venv/bin/libtmux-mcp

0.1sclaimedno tools/list reply (exit 0)

0.1sprocessscript backend runs setup only

Static findings

CRITICAL

Destructive command against a filesystem root or devicesrc/libtmux_mcp/middleware.py:627 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

HIGH

Collapsed <details> block carrying instructionsdocs/clients.md:53 · Collapsed <details> block carrying instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.

AST01

MEDIUM

Python subprocess execution detectedsrc/libtmux_mcp/tools/buffer_tools.py:318 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

MEDIUM

Process kill commandsrc/libtmux_mcp/tools/pane_tools/lifecycle.py:97 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Python subprocess execution detectedsrc/libtmux_mcp/tools/pane_tools/io.py:61 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

MEDIUM

Process kill commandsrc/libtmux_mcp/tools/server_tools.py:152 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Process kill commandsrc/libtmux_mcp/_utils.py:267 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Process kill commandsrc/libtmux_mcp/_utils.py:232 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Process kill commandsrc/libtmux_mcp/tools/pane_tools/lifecycle.py:58 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Process kill commandsrc/libtmux_mcp/_tmux_proc.py:30 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Process kill commandsrc/libtmux_mcp/_utils.py:229 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

HIGH

Destructive file system command detectedsrc/libtmux_mcp/middleware.py:627 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Process kill commandsrc/libtmux_mcp/tools/server_tools.py:170 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Python subprocess execution detectedsrc/libtmux_mcp/tools/buffer_tools.py:369 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

HIGH

Credential pass-through configurationsrc/libtmux_mcp/tools/server_tools.py:109 · Credential pass-through configuration — agent relays sensitive credentialsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.

AST02

MEDIUM

Process kill commandsrc/libtmux_mcp/_utils.py:273 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Process kill commandsrc/libtmux_mcp/tools/window_tools.py:313 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Process kill commandsrc/libtmux_mcp/tools/pane_tools/lifecycle.py:112 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Process kill commandsrc/libtmux_mcp/tools/session_tools.py:237 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

HIGH

Credential pass-through configurationsrc/libtmux_mcp/tools/window_tools.py:204 · Credential pass-through configuration — agent relays sensitive credentialsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.

AST02

MEDIUM

Process kill commandsrc/libtmux_mcp/_utils.py:323 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

HIGH

Credential pass-through configurationsrc/libtmux_mcp/tools/session_tools.py:151 · Credential pass-through configuration — agent relays sensitive credentialsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.

AST02

MEDIUM

Python subprocess execution detectedsrc/libtmux_mcp/tools/pane_tools/io.py:789 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

MEDIUM

Python subprocess execution detectedsrc/libtmux_mcp/tools/buffer_tools.py:220 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

MEDIUM

Process kill commandsrc/libtmux_mcp/tools/session_tools.py:269 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Process kill commandsrc/libtmux_mcp/tools/session_tools.py:256 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Process kill commandsrc/libtmux_mcp/_tmux_proc.py:102 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Python subprocess execution detectedtests/test_history.py:415 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

MEDIUM

Python subprocess execution detectedtests/test_history.py:461 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

MEDIUM

Process kill commandtests/test_utils.py:443 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Python subprocess execution detectedtests/test_server.py:255 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

MEDIUM

Python subprocess execution detectedtests/test_server.py:331 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

LOW

Fake instruction boundary tagdocs/prompts.md:45 · Fake instruction boundary tag · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.

AST01

MEDIUM

Python subprocess execution detectedtests/test_server.py:358 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

MEDIUM

Python subprocess execution detectedtests/test_server.py:171 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

MEDIUM

Python subprocess execution detectedtests/test_server.py:208 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

MEDIUM

Process kill commandsrc/libtmux_mcp/tools/window_tools.py:336 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

Cost to the agent

Instructions loaded

≈1,721 tok

3 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

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

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

22 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 tmux-python: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
Does not do what the description says≈ +5 on the totalIn the sandbox the skill never performed the task it claims (no call to the service it is for). Make sure the happy path runs without extra setup, or describe the real behavior.
Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.

Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim tmux-python Propose a patch to the maintainer