mcp-skill@0.4.0
VERIFIED· install onlyPublisher claims: "Convert any MCP server into an Agent Skill" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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: 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
BUFFER_API_KEYMCP_SKILL_OAUTH_CALLBACK_PORTor--oauth-client-id/--oauth-client-secret/--oauth-scopes/--oauth-client-metadata-url- Where it talks to
- airtable.com (its own)Also buffer.com, canva.com, clickup.com, context7.com, linear.app, notion.com, parallel.ai, claude.com, sentry.dev, canva.link, amazonaws.com, notion.so, sentry.io — 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 buffer.com, canva.com, clickup.com, context7.com, linear.app, notion.com, parallel.ai, claude.com, sentry.dev, canva.link, amazonaws.com, notion.so, sentry.io as well as its own vendor. The guard injects BUFFER_API_KEY, MCP_SKILL_OAUTH_CALLBACK_PORT only into requests to airtable.com (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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-09 and scored it 91/100 (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 · 0 s · 1 scenarios · 0 deviationsStatic findings
result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.No other findings across 11,040 lines in 59 files.
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
No advisories in OSV for mcp-skill@0.4.0 as of 5d ago. This is the package itself, not its dependencies.