Skills/PyPI/onekey-mcp

onekey-mcp@0.1.4

CAUTION· install only

Publisher claims: "Open MCP Marketplace, Official OneKeyMCP Router Connection, MCP Registry, MCP client, OneKey MCP Router, MCP Tool Search of commercial MCPs" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher aiagenta2z · publishing for 554 daysInstalls 60Last detonated 20 h ago
What would fix thisWatchDispute verdict

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

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
MCP_MARKETPLACE_API_KEY
Where it talks to
no vendor host named in the codeAlso deepnlp.org, pulsemcp.com, aliyun.com, aliyuncs.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
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names deepnlp.org, pulsemcp.com, aliyun.com, aliyuncs.com as well as its own vendor. The guard injects MCP_MARKETPLACE_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx onekey-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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-13 and scored it 71/100 (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; Access to sensitive file paths; OS command execution function call detected. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

CRITICAL
OS command execution function call detectedsrc/mcp_marketplace/utils.py:8 · OS command execution function call detectedresult = os.system(command)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/mcp_marketplace/app/mcp_tool_use/src/qwen/qwen_general_api.py:31 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesraise ValueError("qwen_general_api.py call_qwen_max_user_prompt api_key not found, please check .env file key QWEN_API_KEY")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_marketplace/app/mcp_tool_use/src/mcp_servers.py:1558 · Python subprocess execution detectedresult = subprocess.run(command_to_run, capture_output=True, text=True, env=process_env, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/mcp_marketplace/app/mcp_tool_use/src/mcp_servers.py:586 · Process kill command — agent can terminate processesprocess.kill() # Force killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
OS command execution function call detectedsrc/mcp_marketplace/utils.py:20 · OS command execution function call detectedresult = os.system(command)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathspyproject.toml:72 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files, "src/**/*.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)src/mcp_marketplace/app/mcp_tool_use/src/mcp_servers.py:199 · MCP server using network transport (SSE/HTTP) — data sent over networkif mcp_server_type == MCP_TYPE_SSE:Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Access to sensitive file pathssrc/mcp_marketplace/app/mcp_tool_use/src/global_variables.py:281 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file=".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)src/mcp_marketplace/app/mcp_tool_use/src/mcp_servers.py:526 · MCP server using network transport (SSE/HTTP) — data sent over networkif mcp_server_type == MCP_TYPE_SSE:Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
File type combined with upload actionsrc/mcp_marketplace/app/mcp_tool_use/web/static/scripts/scripts.js:724 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('Upload Successfully:', data);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/mcp_marketplace/app/mcp_tool_use/web/static/scripts/scripts.js:709 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Uploading File: ${file.name} to ${url}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈70 tok
1 file · 54 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for onekey-mcp@0.1.4 as of 20 h ago. This is the package itself, not its dependencies.

What would make this Verified

9 points 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 aiagenta2z: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. 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.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim aiagenta2zPropose a patch to the maintainer