Skills/PyPI/mcp-leash

mcp-leash@0.7.0

CAUTION· not started

Publisher claims: "Runtime permission firewall for MCP servers (stdio proxy)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher calasdan-sketch · publishing for 22 daysInstalls 0Last detonated 6d 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

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Not enough was observed to say yet. Not started: dependency install failed; the server itself was not observed. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try mcp-leash` runs it now and prints the full answer.

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 2026-11-08 and scored it 65/100 (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; Destructive file system command detected; Destructive command against a filesystem root or device. 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
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
Destructive command against a filesystem root or devicetests/test_jail.py:586 · Destructive command against a filesystem root or device"params": {"name": "run_cmd", "arguments": {"cmd": "rm -rf /"}}}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsmcp_leash/jail.py:761 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesallowlist on paths must not be a door to `/srv/data/../../etc/passwd`.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_jail.py:367 · Destructive command against a filesystem root or deviceok, reason = jail_mod.tool_allowed(pol, "run_cmd", {"cmd": "rm -rf /"})Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedmcp_leash/jail.py:1285 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Destructive file system command detectedmcp_leash/jail.py:694 · Destructive file system command detected["rm", "-rf", "/"] is also seen as "rm -rf /"."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagemcp_leash/cli.py:6 · npx invocation of non-well-known package — may execute untrusted codemcp-leash --policy policy.json -- npx -y some-mcp-serverFix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Destructive command against a filesystem root or devicemcp_leash/jail.py:694 · Destructive command against a filesystem root or device["rm", "-rf", "/"] is also seen as "rm -rf /"."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsmcp_leash/jail.py:203 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# /srv/data/../../etc/passwd -- or, with a Windows prefix,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_jail.py:2239 · Destructive command against a filesystem root or device"args": {"cmd": "rm -rf /"}, "at": 1700000000}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagemcp_leash/cli.py:258 · npx invocation of non-well-known package — may execute untrusted code"mcp-leash --policy p.json -- npx -y srv")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Destructive command against a filesystem root or devicetests/test_jail.py:1334 · Destructive command against a filesystem root or devicepol, "run_cmd", {"cmd": "rm -rf /"})[0])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_jail.py:455 · Destructive command against a filesystem root or devicepol, "run_cmd", {"cmd": "rm -rf /", "count": 3})Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandmcp_leash/jail.py:1447 · Process kill command — agent can terminate processes"""While active, the signals of _stop_signals() do not kill the jail: theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_jail.py:399 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filespol, "read_file", {"path": {"$ref": "/etc/passwd"}})Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Unicode escape sequence detectedtests/test_jail.py:3755 · Unicode escape sequence detected — may contain obfuscated payloads"\uff4d\uff45\uff54\uff48\uff4f\uff44", "method\u200b", " method",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Destructive file system command detectedtests/test_jail.py:586 · Destructive file system command detected"params": {"name": "run_cmd", "arguments": {"cmd": "rm -rf /"}}}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_jail.py:367 · Destructive file system command detectedok, reason = jail_mod.tool_allowed(pol, "run_cmd", {"cmd": "rm -rf /"})Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_jail.py:427 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"files": [{"path": "/tmp/a"}, {"path": "/etc/shadow"}]})[0])Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive file system command detectedtests/test_jail.py:1334 · Destructive file system command detectedpol, "run_cmd", {"cmd": "rm -rf /"})[0])Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_jail.py:451 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filespol, "read_file", {"path": "/etc/passwd", "x": {"path": "/tmp/a"}})Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive file system command detectedtests/test_jail.py:2239 · Destructive file system command detected"args": {"cmd": "rm -rf /"}, "at": 1700000000}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_jail.py:455 · Destructive file system command detectedpol, "run_cmd", {"cmd": "rm -rf /", "count": 3})Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_jail.py:935 · Process kill command — agent can terminate processes"""Round-3 panel findings: response handling must never kill the proxy."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_jail.py:4548 · Process kill command — agent can terminate processesstops it: SIGTERM, then a kill (terminate() on Windows). It used to stopFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_jail.py:2279 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_jail.py:1151 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files{"path": "/etc/passwd"})Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_jail.py:397 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filespol, "read_file", {"path": "/etc/passwd"})[0])Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/test_jail.py:3432 · 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
Python subprocess execution detectedtests/test_jail.py:889 · 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
Python subprocess execution detectedtests/test_jail.py:3033 · 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
Python subprocess execution detectedtests/test_jail.py:1982 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈49 tok
1 file · 19 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-leash@0.7.0 as of 6d ago. This is the package itself, not its dependencies.

What would make this Verified

15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim calasdan-sketch: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  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. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim calasdan-sketchPropose a patch to the maintainer