Skills/Glama/agent-notebook

agent-notebook@0.1.0

CAUTION· startup only

Publisher claims: "Enables AI agents to read and write a local-first Markdown/Obsidian notebook via a single capture call that routes text into the right notebook, board, or daily journal entry and returns related notes, alongside search, note and card management, and numeric metric series. Access is governed by per-agent tokens with read/write/admin scopes, optional folder restrictions, and an audit log of every action." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher penny777btc · publishing for 3 daysInstalls 0Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials
Needs
AGENT_NOTEBOOK_TOKEN — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

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
AGENT_NOTEBOOK_TOKENConfiguration, not credentials: AGENT_NOTEBOOK_AGENT, AGENT_NOTEBOOK_HOME, AGENT_NOTEBOOK_TRUST_LOOPBACK, AGENT_NOTEBOOK_URL, AGENT_NOTEBOOK_VAULT, ANTHROPIC_BASE_URL
Where it talks to
no vendor host named in the codeAlso githubusercontent.com, nodesource.com, tailscale.com, evil.example, ok.example, x.ai — 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
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names githubusercontent.com, nodesource.com, tailscale.com, evil.example, ok.example, x.ai as well as its own vendor. The guard injects AGENT_NOTEBOOK_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$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 (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-11 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Direct script execution from GitHub raw URL; Pipe-to-shell pattern. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 48 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
7.2sprocessdependency install exit 0
27sprocessrelaunched with a decoy AGENT_NOTEBOOK_TOKEN (tagged; nothing real)
47sclaimedstartup only: exited before answering, asking for AGENT_NOTEBOOK_TOKEN (a decoy value was refused)
47sprocessscript backend runs setup only
47sprocessno install scripts to re-run

Static findings

HIGH
Privileged sudo commandscripts/deploy-linux.sh:10 · Privileged sudo command — agent may execute with elevated privileges# Run it as a dedicated unprivileged user (e.g. `sudo useradd -m notebook`, then `sudo -u notebook -H bash`), not asFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Direct script execution from GitHub raw URLscripts/deploy-linux.sh:6 · Direct script execution from GitHub raw URL — unverified code source# curl -fsSL https://raw.githubusercontent.com/Penny777btc/agent-notebook/main/scripts/deploy-linux.sh | bashFix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Pipe-to-shell patternscripts/deploy-linux.sh:6 · Pipe-to-shell pattern — downloads and immediately executes remote code# curl -fsSL https://raw.githubusercontent.com/Penny777btc/agent-notebook/main/scripts/deploy-linux.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Dense URL-encoded contentscripts/smoke-sanitize.mjs:61 · Dense URL-encoded content — may be obfuscating payloadskeep('<a class="wikilink" href="#/note/%E8%B4%A2%E5%8A%A1%2F2026-11-01.md" title="财务/2026-11-01.md">财务</a>', 'a.wikilink[href^="#/note/"][title]');Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File type combined with upload actionscripts/smoke-sanitize.mjs:55 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`ok 1 ${hostile.length} hostile inputs come out inert (raw HTML and through Markdown)`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Dense URL-encoded contentscripts/smoke-auth.mjs:56 · Dense URL-encoded content — may be obfuscating payloadsassert.equal(resolveSource({ header: '%E7%83%AD%E9%97%A8%E6%90%9C%E7%B4%A2', principal }), '热门搜索');Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
CRITICAL
Pipe-to-shell patternscripts/deploy-linux.sh:118 · Pipe-to-shell pattern — downloads and immediately executes remote codeif ! command -v tailscale >/dev/null; then curl -fsSL https://tailscale.com/install.sh | sh >/dev/null; fiFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Access to sensitive file pathssrc/agents.js:87 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files`[mcp_servers.${SERVER_NAME}.env]`,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/agents.js:116 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn e?.env?.AGENT_NOTEBOOK_TOKEN || e?.environment?.AGENT_NOTEBOOK_TOKEN || null;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/agents.js:110 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst m = txt.match(new RegExp(`\\[mcp_servers\\.${SERVER_NAME}\\.env\\][^\\[]*?AGENT_NOTEBOOK_TOKEN\\s*=\\s*"([^"]+)"`));Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/agents.js:143 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// drop any previous [mcp_servers.agent-notebook] / .env blocksFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandscripts/deploy-linux.sh:27 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get update -qqFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/cli.js:102 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`HTTP clients: POST http://127.0.0.1:${auth.config.port}/mcp with Authorization: Bearer ${t.token}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Privileged sudo commandscripts/deploy-linux.sh:23 · Privileged sudo command — agent may execute with elevated privilegesneed_sudo() { if ! sudo -n true 2>/dev/null; then echo "(需要 sudo 密码来安装软件 / 写 systemd)"; fi; }Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shellscripts/deploy-linux.sh:6 · Remote installer piped to shell# curl -fsSL https://raw.githubusercontent.com/Penny777btc/agent-notebook/main/scripts/deploy-linux.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Access to sensitive file pathssrc/agents.js:144 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst block = new RegExp(`^\\[mcp_servers\\.${SERVER_NAME}(\\.env)?\\]\\n(?:(?!^\\[).*\\n?)*`, 'gm');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Pipe-to-shell patternweb/app.js:1050 · Pipe-to-shell pattern — downloads and immediately executes remote code…ropic-ai/claude-code && claude ，登录后回到这里刷新。' : cliName === 'grok' ? ' 安装并登录：终端运行 curl -fsSL https://x.ai/cli/install.sh | bash 再运行 grok 登录，登录后回到这里刷新。' : ' 安装并登录：终端运行 npm i -g @openai/codex && codex ，登录后回到这里…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Remote installer piped to shellscripts/deploy-linux.sh:118 · Remote installer piped to shellif ! command -v tailscale >/dev/null; then curl -fsSL https://tailscale.com/install.sh | sh >/dev/null; fiFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shellweb/app.js:1050 · Remote installer piped to shell…ropic-ai/claude-code && claude ，登录后回到这里刷新。' : cliName === 'grok' ? ' 安装并登录：终端运行 curl -fsSL https://x.ai/cli/install.sh | bash 再运行 grok 登录，登录后回到这里刷新。' : ' 安装并登录：终端运行 npm i -g @openai/codex && codex ，登录后回到这里…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07

Cost to the agent

Instructions loaded
≈1,317 tok
1 file · 32 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Unclaimed publisher≈ +8 on the totalClaim penny777btc: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. Dense URL-encoded content≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim penny777btcPropose a patch to the maintainer