Skills/Glama/whatsapp-mcp

whatsapp-mcp@0.0.1

CAUTION· install only

Publisher claims: "Enables MCP clients such as ChatGPT, Claude, or Grok to search and read a user's own WhatsApp message history through a linked device, without sending, editing, or deleting messages." Observed in sandbox: reads credential files.

Registry GlamaPublisher engdawood · publishing for 14 daysInstalls 0Last detonated 1 h ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 4 of 4 bundled scripts run with no arguments, with decoy credentials in the environment · 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
CLOUDFLARE_API_TOKENOAUTH_KVOAUTH_PROVIDERWA_OWNER_PASSWORDConfiguration, not credentials: ALERT_EMAIL, ALERT_FROM, ALERT_TO, CLOUDFLARE_ACCOUNT_ID, CONTACT_X, DEFAULT_COUNTRY_CODE, LOGIN_URL, MAX_DB_MB, MAX_MESSAGES, OPEN_SIGNUP, OPERATOR_NAME, REGISTRY, SIGNUP_LIMIT, TIMEZONE, TRANSCRIBE_MODEL, WA_PIN
Where it talks to
whatsapp.net, whatsapp.com (its own)Also x.com, cloudflare.com, finereli.com, claude.ai, chatgpt.com, grok.com — not the publisher's domain; check what for before connecting.
What we saw when it ran
read ~/.npmrc · reached only registry.npmjs.org
What we could not test
use of the skill by an agent

Connect it only under the guard, with no real credential files on the machine it runs on. It read ~/.npmrc, which is nothing an MCP server needs from a user. `--contain` makes those directories unreadable.

$vet-skills run --contain --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 (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-21 and scored it 72/100 (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: reads credential files.

Behavior trace

Honeypot run · 16 s · 3 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.1sprocessexited 1: Node.js v22.23.5
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1: Set CLOUDFLARE_API_TOKEN (a token that can read Workers settings).
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 1: Node.js v22.23.5
0.3sprocessbundled script run in the sandbox with no arguments
15sfilesystemread ~/.npmrc
15sfilesystemread ~/.npm/_logs · ~/.npm/_cacache/index-v5/60/87/13cf84470afa8225bb765aee32de1c70abd5036c1255b2545b2e0844cf16 · ~/.npm/_npx/32026684e21afda6/package.json · ~/.npm/_npx/32026684e21afda6/node_modules/.package-lock.json · ~/.npm/_npx/32026684e21afda6/package-lock.json · ~/.npm/_npx/32026684e21afda6/node_modules outside project
15sfilesystemwrote ~/.npm/_cacache/tmp/ac302b62 · ~/.npm/_cacache/index-v5/60/87/13cf84470afa8225bb765aee32de1c70abd5036c1255b2545b2e0844cf16 · ~/.npm/_cacache/tmp/b119d388 · ~/.npm/_cacache/tmp/3b0db04c · ~/.npm/_cacache/tmp/1714f53a · ~/.npm/_cacache/index-v5/3a/00/b44a61168953f71db98f0b3f9a1a300301abbb38f047c26d945bd049f1ed
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://registry.npmjs.org:443
15sprocessexec /usr/local/bin/npx
15sprocessbundled script run in the sandbox with no arguments
15sprocessexited 1: Node.js v22.23.5
15sprocess4 of 4 bundled scripts run with no arguments
15sprocessscript backend runs setup only
15sprocessscript backend runs setup only
16sprocesssecond launch, clock +45 days, CI unset
16sprocessexited 1: Node.js v22.23.5

Static findings

MEDIUM
Access to sensitive file pathscompose.yml:6 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file: .envFix: 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 packageAGENTS.md:41 · npx invocation of non-well-known package — may execute untrusted code4. Done means all three are green: `npm test`, `npm run typecheck`, and `npx wrangler deploy --dry-run --outdir /tmp/dryrun` (proves the bundle builds).Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Destructive file system command detectedDockerfile:7 · Destructive file system command detected&& rm -rf /var/lib/apt/lists/* \Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathscompose.yml:8 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesPUBLIC_HOST: ${PUBLIC_HOST:?set PUBLIC_HOST in .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 pathsdocker/entrypoint.sh:5 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesecho "Neither WA_OWNER_PASSWORD nor OPEN_SIGNUP=true is set in .env, so nobody can sign in." >&2Fix: 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 actionsrc/whatsapp/account.ts:195 · File type combined with upload action — agent may exfiltrate local data filesinitSchema(this.host.ctx.storage.sql); // puts the trigger backFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/store/store.ts:358 · File type combined with upload action — agent may exfiltrate local data filesconst sentAsLid = written(this.sql.exec(`DELETE FROM lid_senders WHERE sender = ?`, L)) > 0;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 packagedocker/entrypoint.sh:13 · npx invocation of non-well-known package — may execute untrusted codeexec npx wrangler dev --ip 0.0.0.0 --port 8787 --persist-to /data \Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionsrc/store/store.ts:362 · File type combined with upload action — agent may exfiltrate local data filesthis.sql.exec(`UPDATE messages SET sender = ?, data = ? WHERE chat = ? AND id = ?`, P, this.vault.seal(blob, MSG), r.chat, r.id);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/store/store.ts:454 · File type combined with upload action — agent may exfiltrate local data filesconst existing = this.sql.exec<{ sender: string | null; data: ArrayBuffer }>(`SELECT sender, data FROM messages WHERE chat = ? AND id = ?`, cid, ev.id).toArray()[0];Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/store/store.ts:480 · File type combined with upload action — agent may exfiltrate local data filesthis.sql.exec(`UPDATE messages SET sender = COALESCE(sender, ?), data = ? WHERE chat = ? AND id = ?`, sender, this.vault.seal(blob, MSG), cid, ev.id);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 packagescripts/pull-config.mjs:126 · npx invocation of non-well-known package — may execute untrusted codeconsole.log(`Check it with: npx wrangler deploy -c ${out} --dry-run`);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionsrc/store/store.ts:359 · File type combined with upload action — agent may exfiltrate local data filesif (sentAsLid) for (const r of this.sql.exec<{ chat: string; id: string; data: ArrayBuffer }>(`SELECT chat, id, data FROM messages WHERE sender = ?`, L).toArray()) {Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈1,379 tok
3 files · 53 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

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Reads credential files≈ +27 on the totalThe sandbox saw reads under ~/.ssh, ~/.aws, ~/.npmrc, ~/.config or similar. Read only files inside the project, and only the ones the task needs. Seen: ~/.npmrc.
  2. Unclaimed publisher≈ +8 on the totalClaim engdawood: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. 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.
  4. 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.
  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. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim engdawoodPropose a patch to the maintainer