universal-mcp-applications@0.1.40
VERIFIED· install onlyPublisher claims: "A Universal MCP Application: universal_mcp_applications" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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.
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 deviationsStatic findings
"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.subprocess.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.subprocess.run(command, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
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.