Skills/PyPI/murf-mcp

murf-mcp@0.1.14

CAUTION· not started

Publisher claims: "An MCP server for interacting with Murf APIs" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pypi · publishing for 723 daysInstalls 50Last detonated 39 h 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
MURF_API_KEYConfiguration, not credentials: MURF_OUTPUT_DIR
Where it talks to
murf.ai (its own)Also gyan.dev, buildwithfern.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 with a scoped credential, under the guard, and read the third-party hosts first. The code names gyan.dev, buildwithfern.com as well as its own vendor. The guard injects MURF_API_KEY only into requests to murf.ai (and its subdomains) and refuses the rest.

$vet-skills run --secrets MURF_API_KEY=murf.ai -- uvx murf-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 2026-11-12 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: OS command execution function call 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
Python subprocess execution detectedmurf_mcp/claude_setup.py:168 · Python subprocess execution detectedsubprocess.run(["uv", "run", "--python", "[email protected]", "--", "python", "--version"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Prompt injectionREADME.md:94 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…e MCP server is running and tools are available. **Note:** For Windows users, "Developer Mode" must be enabled in Claude Desktop to utilize the MCP server. To enable it, cli…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
OS command execution function call detectedmurf_mcp/utils.py:61 · OS command execution function call detectedcode = os.system(f"open '{file_path}'")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Authorization escalation languageREADME.md:94 · Authorization escalation language · informational: not an instruction file…e MCP server is running and tools are available. **Note:** For Windows users, "Developer Mode" must be enabled in Claude Desktop to utilize the MCP server. To enable it, cli…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedmurf_mcp/setup_docs_mcp/process.py:9 · Python subprocess execution detectedcompleted = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedmurf_mcp/claude_setup.py:170 · Python subprocess execution detectedif subprocess.run(["which", "brew"], capture_output=True).returncode != 0:Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedmurf_mcp/claude_setup.py:175 · Python subprocess execution detectedsubprocess.run(["brew", "install", "ffmpeg"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedmurf_mcp/claude_setup.py:173 · Python subprocess execution detectedif subprocess.run(["which", "ffmpeg"], capture_output=True).returncode != 0:Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagemurf_mcp/setup_docs_mcp/harnesses/claude_desktop.py:52 · npx invocation of non-well-known package — may execute untrusted code"npx not found; install Node.js to bridge the remote docs MCP",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Context shift attemptREADME.md:94 · Context shift attempt — trying to change operational mode · informational: not an instruction file…lick the hamburger menu in the top-left corner, select "Help," and then choose "Enable Developer Mode." --- ## Usage * Prompt the LLM to create a voiceover: For example: …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
OS command execution function call detectedmurf_mcp/utils.py:63 · OS command execution function call detectedcode = os.system(f"xdg-open '{file_path}'")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedmurf_mcp/claude_setup.py:27 · Python subprocess execution detectedresult = subprocess.run([command, 'uvx'], capture_output=True, text=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagemurf_mcp/setup_docs_mcp/harnesses/claude_desktop.py:45 · npx invocation of non-well-known package — may execute untrusted codenpx = npx_bin()Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈46 tok
1 file · 32 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 murf-mcp@0.1.14 as of 38 h ago. This is the package itself, not its dependencies.

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Unclaimed publisher≈ +8 on the totalClaim pypi: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim pypiPropose a patch to the maintainer