Skills/PyPI/universal-mcp-applications

universal-mcp-applications@0.1.40

VERIFIED· install only

Publisher claims: "A Universal MCP Application: universal_mcp_applications" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher universal-mcp · publishing for 556 daysInstalls 637Last detonated 11 min ago
$claude mcp add universal-mcp-applications -- uvx universal-mcp-applications
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 56 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · 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: Verified 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
E2B_API_KEYPROXY_PASSWORDUNIPILE_API_KEYUNIPILE_DSNConfiguration, not credentials: PROXY_PORT, PROXY_USERNAME
Where it talks to
no vendor host named in the codeAlso linkedin.com, microsoft.com, twilio.com, ahrefs.com, airtable.com, apollo.io, bill.com, braze.com, calendly.com, canva.com, clickup.com, coda.io, dialpad.com, figma.com, githubusercontent.com, premierleague.com, gong.io, hashnode.com, heygen.com, hubapi.com, petspot.com, example.org, klaviyo.com, miro.com, youtube.com, yourwebhooklistener.com, neon.tech, agentr.dev, notion.com, posthog.com — not the publisher's domain; check what for before connecting.
What we saw when it ran
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 linkedin.com, microsoft.com, twilio.com, ahrefs.com, airtable.com, apollo.io, bill.com, braze.com, calendly.com, canva.com, clickup.com, coda.io, dialpad.com, figma.com, githubusercontent.com, premierleague.com, gong.io, hashnode.com, heygen.com, hubapi.com, petspot.com, example.org, klaviyo.com, miro.com, youtube.com, yourwebhooklistener.com, neon.tech, agentr.dev, notion.com, posthog.com as well as its own vendor. The guard injects E2B_API_KEY, PROXY_PASSWORD, UNIPILE_API_KEY, UNIPILE_DSN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx universal-mcp-applications

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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 89/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 3 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.7sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.8sprocessexited 1: ModuleNotFoundError: No module named 'typer'
0.8sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.9sprocessbundled script run in the sandbox with no arguments · not named in the instructions
1.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
1.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
1.1sprocessexec /app/apps/web/node_modules/.bin/uv
1.1sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/uv
1.1sprocessexec /app/node_modules/.bin/uv
1.1sprocessexec /pnpm/uv
1.1sprocessexec /usr/local/sbin/uv
1.1sprocessexec /usr/local/bin/uv
1.1sprocessexec /usr/sbin/uv
1.1sprocessexec /usr/bin/uv
1.1sprocessexec /sbin/uv
1.1sprocessexec /bin/uv
1.1sprocessexited 1: PermissionError: [Errno 13] Permission denied: 'uv'
1.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
1.1sprocessexited 1: PermissionError: [Errno 13] Permission denied: 'python'
1.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
1.2sprocessexited 1: ModuleNotFoundError: No module named 'universal_mcp'
1.2sprocess8 of 56 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
1.2sprocessscript backend runs setup only
1.2sprocessscript backend runs setup only
1.2sprocessno install scripts to re-run

Static findings

HIGH
URL with embedded credentialssrc/universal_mcp/applications/dialpad/app.py:4794 · URL with embedded credentials — may be phishing or credential leaking"https://username:[email protected]" is not supported for security reasons. Launching native apps is also supported through a format such as "customuri://domain.com"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Python subprocess execution detectedsrc/scripts/readme.py:103 · Python subprocess execution detectedsubprocess.run(["uv", "run"] + command, check=True, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/scripts/run_docgen.py:21 · Python subprocess execution detectedsubprocess.run(command, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈58 tok
1 file · 81 in bundle

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

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.