Skills/PyPI/mcpdone-audit

mcpdone-audit@0.11.3

CAUTION· not started

Publisher claims: "Static analyzer for MCP server repos, Python and TypeScript/JavaScript: 10 checks (BadHost / Starlette CVE-2026-48710, FastMCP wrapper-layer asyncio.run bug, loose tool schemas, subprocess command-injection w/ cross-function taint propagation, destructive-filesystem sinks from tool params, keyword-guarded SQL read-only bypass, and a TS engine covering DNS-rebinding-unprotected HTTP transports / CVE-2025-66414, child_process injection, destructive fs sinks, and unconstrained zod tool schemas)." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher alienbushman · publishing for 137 daysInstalls 170Last detonated 4d 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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso mcpdone.com — not the publisher's domain; check what for before connecting.
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; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx mcpdone-audit

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 2026-11-10 and scored it 69/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hidden zero-width characters detected; Destructive file system command detected; OS command execution function call 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
Process kill commandtests/test_ts_dns_rebinding.py:708 · Process kill command — agent can terminate processesthis, `_shadowed_transport_names` would be a silent kill switch."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_command_injection.py:45 · Python subprocess execution detectedassert "subprocess.run([" in f.remediationFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
OS command execution function call detectedtests/fixtures/command_injection_bad/server.py:36 · OS command execution function call detectedreturn os.popen("cat " + path).read()Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/fixtures/command_injection_bad/server.py:65 · Python subprocess execution detectedthen into subprocess.run(..., shell=True)."""Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/fixtures/command_injection_good/server.py:21 · Python subprocess execution detectedreturn subprocess.run(["git", "checkout", branch], check=True).argsFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Hidden zero-width characters detectedsrc/mcp_audit/checks/ts_dns_rebinding.py:349 · Hidden zero-width characters detected — may conceal content_WS_CHARS = " \t\r\n\v\f "Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
OS command execution function call detectedtests/fixtures/command_injection_bad/server.py:29 · OS command execution function call detectedos.system(f"sqlite3 mydb.db 'SELECT * FROM {table}'")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/fixtures/command_injection_good/server.py:38 · Python subprocess execution detectedreturn subprocess.run(f"cat {safe}", shell=True, capture_output=True).stdout.decode()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_tstools.py:380 · MCP server using network transport (SSE/HTTP) — data sent over network"""exa-mcp-server passes its raw shape by name from another module.Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Python subprocess execution detectedtests/fixtures/command_injection_good/server.py:28 · Python subprocess execution detectedreturn subprocess.run("uname -a", shell=True, capture_output=True).stdout.decode()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Destructive file system command detectedsrc/mcp_audit/checks/command_injection.py:9 · Destructive file system command detectedcommand string, so anything the model emits as `;rm -rf /` lands.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/fixtures/command_injection_bad/server.py:23 · Python subprocess execution detectedreturn subprocess.run("git log " + branch, shell=True, capture_output=True).stdout.decode()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/fixtures/command_injection_bad/server.py:17 · Python subprocess execution detectedreturn subprocess.run(cmd, shell=True, capture_output=True).stdout.decode()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsmoke_test.py:22 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
OS command execution function call detectedsrc/mcp_audit/checks/command_injection.py:23 · OS command execution function call detected- `os.system(x)` / `os.popen(x)` where `x` contains a tool parameterFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/fixtures/command_injection_good/server.py:51 · Python subprocess execution detectedreturn subprocess.run(["git", "log", "--oneline", branch]).argsFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/fixtures/command_injection_bad/server.py:50 · Python subprocess execution detectedsubprocess.run(cmd, shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_command_injection_cross_function.py:18 · Python subprocess execution detected# execute_query -> _run_shell -> subprocess.run(shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Hidden zero-width characters detectedtests/test_ts_destructive_fs_sink.py:371 · Hidden zero-width characters detected — may conceal content(bom / "server.ts").write_text("" + HDR + body, encoding="utf-8")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Python subprocess execution detectedtests/fixtures/command_injection_good/server.py:14 · Python subprocess execution detectedreturn subprocess.run(["kubectl", *args], capture_output=True).stdout.decode()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_audit/checks/command_injection.py:17 · Python subprocess execution detectedThe safe pattern is `subprocess.run(["git", "checkout", branch])` —Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_audit/checks/command_injection.py:8 · Python subprocess execution detected(a) `subprocess.run(..., shell=True)` — the shell parses the wholeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_audit/checks/command_injection.py:384 · Python subprocess execution detected"`subprocess.run(['git', 'checkout', branch_param], check=True)`. "Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/fixtures/command_injection_bad/server.py:59 · Python subprocess execution detectedreturn subprocess.run(f"git checkout {branch}").argsFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈162 tok
1 file · 81 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 mcpdone-audit@0.11.3 as of 4d ago. This is the package itself, not its dependencies.

What would make this Verified

11 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim alienbushman: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. OS command execution function call detected≈ +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 alienbushmanPropose a patch to the maintainer