Skills/Glama/brainchain-mcp

brainchain-mcp@0.9.2

CAUTION· install only

Publisher claims: "Enables AI agents to post a task with quality levels, have a frontier model hired and graded on BrainChain, and pay only when the delivered work passes, with automatic refunds otherwise." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher usebrainchain · publishing for 7 daysInstalls 0Last detonated 12 h 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
no credential variables read in the code
Where it talks to
usebrainchain.com (its own)Also robinhood.com, shipped.bond, rpc.example, desk.example, base.org — 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 under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable and talks to usebrainchain.com, its own; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- <the server's command>

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 2026-11-14 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. 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
Unicode escape sequence detectedsrc/tools.ts:243 · Unicode escape sequence detected — may contain obfuscated payloadsconst BLANK = /^[\s\p{Cc}\p{Cf}\p{Zl}\p{Zp}\u034f\u115f\u1160\u17b4\u17b5\u180b-\u180f\u2800\u3164\ufe00-\ufe0f\uffa0\u{e0000}-\u{e0fff}]*$/u;Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packagesrc/payments.test.ts:331 · npx invocation of non-well-known package — may execute untrusted codefor (const approveCommand of ["npx -y brainchain-mcp approve", "BRAINCHAIN_PAYER_KEY_FILE=~/.brainchain/payer.key npx -y brainchain-mcp approve"]) {Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/payments.test.ts:69 · npx invocation of non-well-known package — may execute untrusted codereturn createDesk({ config: { ...config, ...overrides }, signer, approveCommand: "npx -y brainchain-mcp approve", fetch: fetchImpl, postTimeoutMs: 10_000 });Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/server.test.ts:399 · npx invocation of non-well-known package — may execute untrusted code"Run `BRAINCHAIN_NETWORK=testnet BRAINCHAIN_PAYER_KEY_FILE=~/.brainchain/payer.key npx -y [email protected] approve` once;",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/grades.test.ts:43 · npx invocation of non-well-known package — may execute untrusted codecreateDesk({ config, signer, approveCommand: "npx -y brainchain-mcp approve", fetch: fetchImpl, postTimeoutMs: 10_000 });Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/server.test.ts:337 · npx invocation of non-well-known package — may execute untrusted codeconst command = "npx -y [email protected] approve";Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.github/workflows/ci.yml:53 · npx invocation of non-well-known package — may execute untrusted coderun: echo | npx -y [email protected] > /dev/nullFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Access to sensitive file pathssrc/server.test.ts:147 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst result = await (await connect({ ...env, BRAINCHAIN_NETWORK: network }, { fetch: fetchImpl })).callTool(call);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/server.test.ts:352 · npx invocation of non-well-known package — may execute untrusted codeconst [assignment] = approveCommand(mainnet, "0.0.0-test", { BRAINCHAIN_PAYER_KEY_FILE: path }).split(" npx ");Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/server.test.ts:365 · npx invocation of non-well-known package — may execute untrusted codeconst approve = "BRAINCHAIN_NETWORK=testnet npx -y [email protected] approve";Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/payments.test.ts:203 · npx invocation of non-well-known package — may execute untrusted codeconst d = createDesk({ config: { ...config, desk: local }, signer, approveCommand: "npx -y brainchain-mcp approve", postTimeoutMs: 500 });Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandsrc/server.ts:48 · File permission modification command — agent changes file ownership/permissionsif (process.platform !== "win32" && (stats.mode & 0o077) !== 0) throw new Error(`${path} can be read by other accounts on this machine. Run chmod 600 on it, then restart the server.`);Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandsrc/server.test.ts:297 · File permission modification command — agent changes file ownership/permissionsif (process.platform !== "win32") expect(() => payerAccount({ BRAINCHAIN_PAYER_KEY_FILE: keyFile(KEY, 0o644) })).toThrow(/can be read by other accounts.*chmod 600/);Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Access to sensitive file pathssrc/bonds.test.ts:55 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst config = resolveConfig({ BRAINCHAIN_NETWORK: "mainnet", BRAINCHAIN_BUDGET_UNITS: "20000000", ...env });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/skill.test.ts:45 · npx invocation of non-well-known package — may execute untrusted codeexpect(body).toContain(`BRAINCHAIN_PAY_ON=${payOn} BRAINCHAIN_PAYER_KEY_FILE=${keyFile} npx -y brainchain-mcp@${version} wallet`);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Access to sensitive file pathssrc/server.test.ts:163 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst client = await connect({ ...env, BRAINCHAIN_DAILY_UNITS: "2000000" }, { log: (message) => logged.push(message) });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Hidden zero-width characters detectedsrc/grades.test.ts:118 · Hidden zero-width characters detected — may conceal contentexpect(() => checkGrade({ brief: "x", result: "​ " })).toThrow("result is empty.");Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
File permission modification commandexamples/openclaw/brainchain/SKILL.md:67 · File permission modification command — agent changes file ownership/permissionschmod 600 ~/.brainchain/payer.keyFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/payments.test.ts:488 · npx invocation of non-well-known package — may execute untrusted codeconst d = createDesk({ config: base, signer, approveCommand: "npx -y brainchain-mcp approve", fetch: fetchImpl, funds: async () => ({ balance: 5_000_000n }) });Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsexamples/openclaw/brainchain/SKILL.md:80 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files`~/.openclaw/.env` or OpenClaw's environment reaches the agent's shell.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathssrc/config.test.ts:62 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfor (const value of ["notaurl", "ftp://example.com", "file:///etc/passwd"]) {Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known package.github/workflows/ci.yml:55 · npx invocation of non-well-known package — may execute untrusted code# outside the checkout, where npx would otherwise resolve this repository's unbuilt package of the same name.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageexamples/openclaw/brainchain/SKILL.md:87 · npx invocation of non-well-known package — may execute untrusted code4. Check the key: `BRAINCHAIN_PAY_ON=base BRAINCHAIN_PAYER_KEY_FILE=~/.brainchain/payer.key npx -y [email protected] wallet`Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageexamples/openclaw/brainchain/SKILL.md:71 · npx invocation of non-well-known package — may execute untrusted code`BRAINCHAIN_PAYER_KEY_FILE=~/.brainchain/payer.key npx -y [email protected] approve` (withFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/server.ts:147 · npx invocation of non-well-known package — may execute untrusted codereturn `${network}${key}npx -y brainchain-mcp@${version} approve`;Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Access to sensitive file pathssrc/server.test.ts:79 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst client = await connect({ ...env, BRAINCHAIN_PAYER_KEY: KEY }, { log: (message) => logged.push(message) });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈2,499 tok
1 file · 39 in bundle

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.

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 usebrainchain: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  3. Unicode escape sequence detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim usebrainchainPropose a patch to the maintainer