brain@0.1.0
VERIFIED· install onlyPublisher claims: "Enables Claude Code to search, read, create, edit, rename, and delete notes in a shared self-hosted markdown vault, and to inspect backlinks, outgoing links, outlines, tags, properties, daily notes, unresolved links, orphans, dead-ends, and templates over Streamable HTTP with bearer-token authentication." 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
BRAIN_TOKENConfiguration, not credentials: BRAIN_ALLOW_LOCAL_REMOTE, BRAIN_CLIENT_SRC, BRAIN_DATA_DIR, BRAIN_DEV, BRAIN_HOST, BRAIN_PORT, BRAIN_SECTION, BRAIN_URL, BRAIN_VAULT_DIR, BRAIN_WEB_DIR- Where it talks to
- no vendor host named in the codeAlso nodejs.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 with a scoped credential, under the guard, and read the third-party hosts first. The code names nodejs.org as well as its own vendor. The guard injects BRAIN_TOKEN 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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 and scored it 80/100 (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
rm -rf /opt/node && mkdir -p /opt/nodeFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.chown -R root:root /opt/brain && chmod -R a+rX /opt/brainFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.rm -rf /opt/brain.old; [ -d /opt/brain ] && mv /opt/brain /opt/brain.oldFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.mkdir -p "$HOME/.config/brain"; chmod 700 "$HOME/.config/brain"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.chmod 700 "$CLAUDE_DIR/hooks/brain-context.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.npx esbuild server/src/main.ts --bundle --platform=node --target=node22 --format=esm \Fix: Pin versions and sources; vendor anything fetched at install time.rm -rf /opt/brain.new && mkdir -p /opt/brain.newFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.expect((await s.req("GET", "/api/v1/note?path=../../etc/passwd")).status).toBe(400);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.ssh "$PVE_HOST" "pct push $VMID /tmp/brain.tar.gz /root/brain.tar.gz && rm /tmp/brain.tar.gz && pct exec $VMID -- bash -c 'cd /root && rm -rf brain && tar xzf brain.tar.gz && bash brain/install.sh'"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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.