Skills/PyPI/mcp-plugin

mcp-plugin@0.1.6

CAUTION· install only

Publisher claims: "Standalone MCP gateway — persistent connections to external MCP servers" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher juzcn · publishing for 79 daysInstalls 327Last detonated 6d 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
GITHUB_TOKENConfiguration, not credentials: MCP_PLUGIN_FILE, SLIFE_AGENT_NAME, SLIFE_PLUGIN_NAME, SLIFE_SESSION_ID
Where it talks to
no vendor host named in the code
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. It asks for GITHUB_TOKEN and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

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

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 2026-11-08 and scored it 78/100 (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; URL with embedded credentials. 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

MEDIUM
Process kill commandmcp_plugin/connection.py:827 · Process kill command — agent can terminate processes# kill this relay (a dead relay wedges the server's stderrFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandmcp_plugin/process.py:274 · Process kill command — agent can terminate processeskill keeps Ctrl‑C exit snappy.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_config.py:58 · MCP server using network transport (SSE/HTTP) — data sent over network"args": ["-y", "anyapi-mcp-server", "--spec", "https://example.com/api.yaml"],Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packagemcp_plugin/config.py:363 · npx invocation of non-well-known package — may execute untrusted code# ── REST-API helpers (rest_apis are ordinary npx anyapi server entries) ─Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandmcp_plugin/platform.py:152 · Process kill command — agent can terminate processes# — kill the whole group safely.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagemcp_plugin/config.py:15 · npx invocation of non-well-known package — may execute untrusted codeare ordinary ``npx anyapi-mcp-server`` entries taggedFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandmcp_plugin/connection.py:398 · Process kill command — agent can terminate processes# ``stream()`` would ``aclose()`` it on exit and kill the readerFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsmcp_plugin/os_detect.py:84 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files``/root/`` or ``/etc/shadow`` are naturally denied by the kernel.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandtests/test_mcp_connection.py:1039 · Process kill command — agent can terminate processeschild shares the plugin's group, teardown can only kill the directFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagemcp_plugin/config.py:376 · npx invocation of non-well-known package — may execute untrusted code"""Build a server entry that serves *name* via ``npx anyapi-mcp-server``.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandmcp_plugin/platform.py:76 · Process kill command — agent can terminate processes5. Wait *force_timeout* seconds for kill to take effect.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
URL with embedded credentialsmcp_plugin/logging.py:338 · URL with embedded credentials — may be phishing or credential leaking# `/` so "https://host:8080/user@domain" (a port + path, NOT credentials) isFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Process kill commandmcp_plugin/connection.py:355 · Process kill command — agent can terminate processes# and can only kill the direct child — the grandchild survives,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandmcp_plugin/platform.py:75 · Process kill command — agent can terminate processes4. Force-kill if still running.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagetests/test_config.py:148 · npx invocation of non-well-known package — may execute untrusted code"""save_rest_api — npx anyapi entry with a fetched_at-stamped source."""Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_mcp_connection.py:343 · MCP server using network transport (SSE/HTTP) — data sent over networkclass TestMCPServerConnectionHTTP:Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Process kill commandmcp_plugin/connection.py:352 · Process kill command — agent can terminate processes# Own process group on POSIX so teardown can kill the wholeFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈53 tok
1 file · 35 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 mcp-plugin@0.1.6 as of 6d ago. This is the package itself, not its dependencies.

What would make this Verified

2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim juzcn: 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. URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. 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.
  6. 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 juzcnPropose a patch to the maintainer