Skills/npm/mcp-newoutlook

mcp-newoutlook@0.32.25

CAUTION· startup only

Publisher claims: "MCP server that lets AI assistants work with New Outlook (web) through a Chrome/Edge extension bridge" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher heeyuncho · publishing for 35 daysInstalls 10,210Last detonated 5d 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

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
no vendor host named in the codeAlso office.com, office365.com, cloud.microsoft, live.com, aka.ms — 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 under the guard. Startup only; authenticated tool behavior not tested. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- npx -y mcp-newoutlook

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 2026-11-09 and scored it 71/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Auto-update or dynamic fetch configuration; Auto-update or dynamic fetch configuration; document.cookie access. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 32 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
12sprocessdependency install exit 0
32sfilesystemwrote ~/.mcp-newoutlook/config.json
32sclaimedstartup only: exited (0) before answering · code: 'ENOENT', syscall: 'open', path: '/tmp/ks-detonate-d8ywU8/task/home/work/acme-api/.claude/skills/mcp-newoutlook/extension/icons/icon.svg' }
32sprocessscript backend runs setup only
32sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagedist/setup.js:134 · npx invocation of non-well-known package — may execute untrusted codereturn { ready: false, runs, warn: true, text: `Launcher not set up (${why}). AI apps start mcp-newoutlook through npx meanwhile, which is slower to start.` };Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationdist/tools.js:77 · Auto-update or dynamic fetch configuration — agent may load new code at runtimereturn (await import("./autoupdate.js")).updateStatus(CONFIG_DIR, SERVER_VERSION, process.env, config);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/bridge.js:586 · Process kill command — agent can terminate processes* up to maxWaitMs for the running ones, since the AI app may kill the process soon after.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagedist/setup.js:146 · npx invocation of non-well-known package — may execute untrusted code* For a server started through npx (an AI app registered before the launcher) with no store yet:Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/launch.cjs:515 · npx invocation of non-well-known package — may execute untrusted codeprocess.stderr.write(`mcp-newoutlook: nothing installed in ${(0, node_path_1.join)(home, "versions")}. Run: npx mcp-newoutlook setup\n`);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationdist/updater.js:4 · Auto-update or dynamic fetch configuration — agent may load new code at runtime// autoupdate.ts's job; this file only knows how.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Prompt injectionREADME.md:67 · Prompt injection — known jailbreak technique reference · informational: not an instruction file- opens the Extensions page of Chrome and/or Edge, and that folder. The one manual step, in the browser you use Outlook in: turn on *Developer mode* and click *Load unpacked* on the folder;Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
npx invocation of non-well-known packagedist/index.js:143 · npx invocation of non-well-known package — may execute untrusted code// Keeps the extension in step with this server, in the background (npx fetches a newer release on start).Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Collapsed <details> block carrying instructionsextension/popup.html:24 · Collapsed <details> block carrying instructions · informational: not an instruction file<summary class="muted">Advanced</summary> <div class="row"> <label for="token">Pairing token (only for mcp-newoutlook before 0.15)</label> <input id="token" typFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
document.cookie accessextension/background.js:517 · document.cookie access — can steal session cookiesconst m = document.cookie.match(/(?:^|;\s*)X-OWA-CANARY=([^;]+)/i);Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
npx invocation of non-well-known packagedist/tools.js:113 · npx invocation of non-well-known package — may execute untrusted code// npx or a clone. Loaded on demand: the updater brings in the MCP client, which startup doesn't need.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/autoupdate.js:140 · npx invocation of non-well-known package — may execute untrusted code// npx and a clone update themselves (npx) or never (a clone): only the store is ours.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/setup.js:25 · npx invocation of non-well-known package — may execute untrusted code* The package from npm, always the latest release: --prefer-online makes npx check npm for aFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/setup.js:222 · File type combined with upload action — agent may exfiltrate local data filesconsole.log("AI apps on this computer:");Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagedist/index.js:29 · npx invocation of non-well-known package — may execute untrusted code// `npx mcp-newoutlook rollback [version]`: the launcher's own command, on this store (#launcher).Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Authorization escalation languageREADME.md:67 · Authorization escalation language · informational: not an instruction file- opens the Extensions page of Chrome and/or Edge, and that folder. The one manual step, in the browser you use Outlook in: turn on *Developer mode* and click *Load unpacked* on the folder;Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagedist/index.js:120 · npx invocation of non-well-known package — may execute untrusted code// Started through npx (registered before the launcher): the store is filled in theFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈63 tok
1 file · 34 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

No advisories in OSV for mcp-newoutlook@0.32.25 as of 5d ago. This is the package itself, not its dependencies.

What would make this Verified

9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim heeyuncho: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  3. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. document.cookie access≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  5. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  6. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim heeyunchoPropose a patch to the maintainer