Skills/Glama/multi-mail

multi-mail@0.2.1

VERIFIED· install only

Publisher claims: "Enables searching, reading, drafting, and sending email across multiple Gmail accounts from Claude Desktop, Claude Code, and ChatGPT, including cross-account search and threaded replies." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher yybd · publishing for 6 daysInstalls 0Last detonated 6d ago
$npx skills add multi-mail
WatchReport an issue

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
CREDENTIALS_PATHGOOGLE_CLIENT_SECRETMCP_AUTH_TOKENMULTI_MAIL_CREDENTIALSConfiguration, not credentials: GOOGLE_CLIENT_ID, MULTI_MAIL_DEFAULT, MULTI_MAIL_HOME, MULTI_MAIL_SEND, MULTI_MAIL_TZ
Where it talks to
no vendor host named in the codeAlso google.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 google.com as well as its own vendor. The guard injects CREDENTIALS_PATH, GOOGLE_CLIENT_SECRET, MCP_AUTH_TOKEN, MULTI_MAIL_CREDENTIALS 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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-08 and scored it 81/100 (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 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

LOW
Collapsed <details> block carrying instructionsREADME.he.md:86 · Collapsed <details> block carrying instructions · informational: not an instruction file<summary>הרצה מקוד המקור</summary> ```bash git clone https://github.com/yybd/multi-mail-mcp.git multi-mail && cd multi-mail && npm install && npm run build ``` Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Collapsed <details> block carrying instructionsREADME.md:95 · Collapsed <details> block carrying instructions · informational: not an instruction file<summary>Running from source instead</summary> ```bash git clone https://github.com/yybd/multi-mail-mcp.git multi-mail && cd multi-mail && npm install && npm ruFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsscripts/test.ts:126 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst srv = spawn('npx', ['tsx', 'src/http.ts'], { env: { ...env, MCP_AUTH_TOKEN: TOKEN, PORT: String(port) }, stdio: 'pipe' });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/gmail.ts:23 · npx invocation of non-well-known package — may execute untrusted codeif (!refresh) throw new Error(`${acc.email} has no refresh token — reconnect it: npx -y @yybd/multi-mail-mcp add`);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/gmail.ts:138 · npx invocation of non-well-known package — may execute untrusted codeif (accounts.length === 0) throw new Error('No Gmail accounts are connected. Run: npx -y @yybd/multi-mail-mcp add');Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Authorization escalation languageREADME.he.md:190 · Authorization escalation language · informational: not an instruction file · informational: not an instruction file(או `ngrok http 3333`.) ב-ChatGPT: **Settings → Apps & Connectors → Advanced → Developer mode** → **Create** →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 packagesrc/calendar.ts:26 · npx invocation of non-well-known package — may execute untrusted code`npx -y @yybd/multi-mail-mcp add ${acc.email} --calendar`Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsscripts/test.ts:148 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst bad = spawn('npx', ['tsx', 'src/http.ts'], { env: { ...env, MCP_AUTH_TOKEN: '' } });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/gmail.ts:46 · npx invocation of non-well-known package — may execute untrusted code`Access to ${acc.email} has expired or was revoked. Reconnect: npx -y @yybd/multi-mail-mcp add ${acc.email}. ` +Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/cli.ts:144 · npx invocation of non-well-known package — may execute untrusted codeif (!accounts.length) return console.log(`No accounts connected yet. Run: npx -y @yybd/multi-mail-mcp add\n(credentials: ${CREDENTIALS_PATH})`);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Prompt injectionREADME.he.md:190 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file(או `ngrok http 3333`.) ב-ChatGPT: **Settings → Apps & Connectors → Advanced → Developer mode** → **Create** →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 packagesrc/config.ts:124 · npx invocation of non-well-known package — may execute untrusted codethrow new Error('No Gmail accounts are connected. Run: npx -y @yybd/multi-mail-mcp add');Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Prompt injectionREADME.md:68 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file…veral accounts of one person in one session isn't documented | yes | yes | yes (developer mode) | only you and Google | | [navbuildz/gmail-mcp-server](https://github.com/navb…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageREADME.he.md:59 · Authorization escalation language · informational: not an instruction file · informational: not an instruction file| [google_workspace_mcp](https://github.com/taylorwilsdon/google_workspace_mcp) (~3.5k ⭐) | ריבוי *משתמשים*. כמה תיבות של אדם אחד באותו סשן לא מתועד | כן | כן | כן (Developer Mode) | רק אצלך ובגוגל |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsscripts/test.ts:113 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfor (const how of [{ args: ['tsx', 'src/main.ts', '--drafts-only'], env }, { args: ['tsx', 'src/main.ts'], env: { ...env, MULTI_MAIL_SEND: 'off' } }]) {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/gmail.ts:443 · npx invocation of non-well-known package — may execute untrusted code`npx -y @yybd/multi-mail-mcp add ${acc.email} --labels`Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Prompt injectionREADME.he.md:59 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file| [google_workspace_mcp](https://github.com/taylorwilsdon/google_workspace_mcp) (~3.5k ⭐) | ריבוי *משתמשים*. כמה תיבות של אדם אחד באותו סשן לא מתועד | כן | כן | כן (Developer Mode) | רק אצלך ובגוגל |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 packagesrc/calendar.ts:41 · npx invocation of non-well-known package — may execute untrusted codethrow new Error('No account has calendar enabled. Run: npx -y @yybd/multi-mail-mcp add <account> --calendar');Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/cli.ts:152 · npx invocation of non-well-known package — may execute untrusted codeUsage: npx -y @yybd/multi-mail-mcp [command]Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsscripts/test.ts:48 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert.equal(safeFilename('../../etc/passwd'), 'passwd');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionscripts/test.ts:121 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('✓ drafts-only (flag and env): no send tools');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 packagesrc/http.ts:25 · npx invocation of non-well-known package — may execute untrusted code'so the HTTP endpoint will not start without one. Generate one with: npx -y @yybd/multi-mail-mcp token'Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Prompt injectionREADME.md:197 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction fileIn ChatGPT, open **Settings → Apps & Connectors → Advanced**, turn on **Developer mode**, then click **Create** and fill in:Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageREADME.md:197 · Authorization escalation language · informational: not an instruction file · informational: not an instruction fileIn ChatGPT, open **Settings → Apps & Connectors → Advanced**, turn on **Developer mode**, then click **Create** and fill in:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageREADME.md:68 · Authorization escalation language · informational: not an instruction file · informational: not an instruction file…veral accounts of one person in one session isn't documented | yes | yes | yes (developer mode) | only you and Google | | [navbuildz/gmail-mcp-server](https://github.com/navb…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈34 tok
1 file · 18 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.

multi-mail@0.2.1 safety verdict: Verified (install only) — KillerSkills