Skills/PyPI/vestibule-mcp

vestibule-mcp@0.1.2

CAUTION· not started

Publisher claims: "A local, kernel-isolated code-execution sandbox for AI agents, exposed as an MCP server." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher victorperson999 · publishing for 9 daysInstalls 414Last detonated 49 min ago

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 codeAlso docker.com — not the publisher's domain; check what for before connecting.
What we saw when it ran
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.

$vet-skills run --net declared -- uvx vestibule-mcp

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 2026-11-20 and scored it 72/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; References a credential file in the home directory; Image alt text carrying instructions. 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
Python exec or eval of computed codesrc/vestibule/backends/native_helper.py:4 · Python exec or eval of computed code`vestibule-warden -S -P -c "exec(open(<fd>,'rb').read())"`, and this file is that programFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python exec or eval of computed codesrc/vestibule/backends/native.py:182 · Python exec or eval of computed code"vestibule-warden", "-S", "-P", "-c", f"exec(open({source},'rb').read())",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Process kill commandsrc/vestibule/backends/container.py:665 · Process kill command — agent can terminate processes# Outlasts the finisher's kill (5 s) + rm -f (5 s), with slack.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandsrc/vestibule/backends/select.py:83 · Privileged sudo command — agent may execute with elevated privileges"(`sudo usermod -aG docker $USER`), log out and back in, then restart your agent. "Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/vestibule/backends/select.py:743 · Python subprocess execution detectedr = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/vestibule/cleanup.py:84 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/vestibule/backends/container.py:443 · Process kill command — agent can terminate processeslog.warning("run %s: timeout after %ds; container kill detached", run_id, timeout_s)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/vestibule/server.py:470 · Python subprocess execution detectedsubprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/vestibule/backends/container.py:412 · Process kill command — agent can terminate processes# overflow kill the container early rather than letting it chatter on.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/vestibule/backends/native_helper.py:449 · Python subprocess execution detectedos.execve(f"{directory}/{name}", cfg["argv"], env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/vestibule/backends/container.py:11 · Process kill command — agent can terminate processesincluding on guest timeout, where the kill is fully detached (§4.5, amended by theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
References a credential file in the home directorysrc/vestibule/backends/select.py:775 · References a credential file in the home directory~/.docker/config.json puts those two words in a WARNING on the first line instead. It doesn'tFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Process kill commandsrc/vestibule/backends/container.py:42 · Process kill command — agent can terminate processesand a POSIX parent's its owner's pid, so a sweep can remove what a hard kill left behindFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Image alt text carrying instructionsREADME.md:9 · Image alt text carrying instructionsTerminal recording. A short program runs twice. On the machine itself it reads a fake key file and connects to 1.1.1.1. Run through Vestibule, the same program Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Image alt text carrying instructionsPYPI.md:9 · Image alt text carrying instructionsTerminal recording. A short program runs twice. On the machine itself it reads a fake key file and connects to 1.1.1.1. Run through Vestibule, the same program Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandsrc/vestibule/server.py:479 · Process kill command — agent can terminate processesstart_new_session=True, # out of reach of a PID kill and of the SDK's killpgFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/vestibule/backends/naive.py:78 · Process kill command — agent can terminate processes# POSIX: its own process group, so a kill reaches the guest's childrenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/vestibule/backends/select.py:62 · Process kill command — agent can terminate processes# S7-D1 shutdown budget. MCP clients close stdin, wait ~2 s, then kill the server'sFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/vestibule/backends/select.py:340 · Process kill command — agent can terminate processes# processes that would outlive the server's exit: kill them with the CLIs.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandsrc/vestibule/unpack.py:14 · File permission modification command — agent changes file ownership/permissionsand the set-id/sticky bits but keep owner rwx, so the cache can be deleted without a chmodFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandsrc/vestibule/server.py:163 · Process kill command — agent can terminate processesexcept Exception as e: # never let an exception kill the sessionFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/vestibule/backends/native.py:427 · Process kill command — agent can terminate processesif truncated: # as M1's CLI reports after its killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/vestibule/cleanup.py:6 · Process kill command — agent can terminate processesruns in its own session, so neither a kill of the server's PID nor a kill of its processFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/vestibule/backends/naive.py:96 · Process kill command — agent can terminate processes# normal teardown used to kill it, but POSIX now exits with os._exit (M2 step 1b).Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/vestibule/backends/select.py:775 · File type combined with upload action — agent may exfiltrate local data files~/.docker/config.json puts those two words in a WARNING on the first line instead. It doesn'tFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/vestibule/backends/naive.py:49 · Process kill command — agent can terminate processes# Guest processes still running, so the POSIX shutdown hand-off can kill themFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/vestibule/server.py:427 · Process kill command — agent can terminate processes"""Snapshot, kill CLIs, start the cleaner, exit 0. Synchronous: no await anywhere, soFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/vestibule/backends/native.py:443 · Process kill command — agent can terminate processes"""S4-D8, from the helper's line of guest/'s counters: `oom_kill` counts any OOM kill inFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/vestibule/backends/naive.py:51 · Process kill command — agent can terminate processes# used to kill them.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈59 tok
1 file · 28 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

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

What would make this Verified

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim victorperson999: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Python exec or eval of computed code≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  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 victorperson999Propose a patch to the maintainer