bellman@0.9.4
VERIFIED· install onlyPublisher claims: "Enables MCP-connected agent sessions across different providers and machines to collaborate in shared rooms, joining via relayable codes to preview and exchange briefs, messages, artifacts, action requests, and a shared read-only working surface. Also serves A2A-speaking agents through a public-room endpoint." 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
MAX_CLIENT_SECRET_CHARSConfiguration, not credentials: BELLMAN_BUS_ROOT, BELLMAN_DOOR_ROOT, BELLMAN_HOSTED_SEAT, BELLMAN_KEYS, BELLMAN_URL, SEND_EMAIL, STRANGER_KEY_PREFIX, SUN_PATH_MAX_BYTES- Where it talks to
- bellman.sh (its own)Also cloudflare-dns.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 cloudflare-dns.com as well as its own vendor. The guard injects MAX_CLIENT_SECRET_CHARS only into requests to bellman.sh (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 2026-11-15 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
console.error(`bellman-mcp-server listening on http://localhost:${port}/mcp`);Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.No other findings across 14,898 lines in 80 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
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.