Skills/Glama/dispatch

dispatch@0.4.0-alpha

CAUTION· install only

Publisher claims: "This MCP server enables AI agents and teams to coordinate through shared inboxes, threaded conversations, attachments, expiring file reservations, prompts, and live notifications, while replaying missed events after restarts." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

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

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
second launch with the clock 45 days ahead · 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
ANTHROPIC_API_KEYDISPATCH_TOKENConfiguration, not credentials: CALL_BACKEND, CALL_MODEL, CALL_PERSONA, DISPATCH_AGENT_KEY, DISPATCH_AUTO_UPDATE, DISPATCH_BACKUP_DIR, DISPATCH_BACKUP_KEEP, DISPATCH_BACKUP_PASSPHRASE, DISPATCH_COOKIE_SECURE, DISPATCH_DATA_DIR, DISPATCH_ICE_SERVERS, DISPATCH_LOG_LEVEL, DISPATCH_MAIL_FILE, DISPATCH_MAIL_FROM, DISPATCH_MCP_URL, DISPATCH_ORIGIN, DISPATCH_PROJECT, DISPATCH_SETUP_KEY, DISPATCH_SMTP_URL, DISPATCH_TRUST_PROXY, DISPATCH_UPDATE_COMMAND, DISPATCH_UPDATE_REPO, DISPATCH_URL, NEXT_PUBLIC_BUILD
Where it talks to
no vendor host named in the codeAlso sameer.sh, huggingface.co — 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 sameer.sh, huggingface.co as well as its own vendor. The guard injects ANTHROPIC_API_KEY, DISPATCH_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; nothing executable in the bundle ran; the trace covers the install step only) 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: Access to sensitive file paths; Access to sensitive file paths; Auto-update or dynamic fetch configuration. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.2sprocesssecond launch, clock +45 days, CI unset

Static findings

HIGH
Access to sensitive file pathsscripts/setup.mjs:5 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env.local",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 pathsapp/login.jsx:264 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesplaceholder="DISPATCH_SETUP_KEY from .env.local"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationlib/updates.mjs:106 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeauto: process.env.DISPATCH_AUTO_UPDATE === "true",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsscripts/setup.mjs:17 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Ready. Your one-time setup key (DISPATCH_SETUP_KEY) is in .env.local. Run npm run dev.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
README directs the reader to a committed installerREADME.md:237`desktop/package.json`, run `npm run desktop:build`, and copy the new `Dispatch-Setup-<version>.exe`, itsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationlib/updates.mjs:136 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeif (process.env.DISPATCH_AUTO_UPDATE !== "true") return;Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiontests/call.mjs:196 · File type combined with upload action — agent may exfiltrate local data filesconsole.log("sending a message does not interrupt the screen share");Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)app/connect.jsx:39 · MCP server using network transport (SSE/HTTP) — data sent over networktext: `[mcp_servers.dispatch]\nurl = "${url}"\nhttp_headers = { Authorization = "Bearer ${token}" }`,Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Credential pass-through configurationlib/log.mjs:1 · Credential pass-through configuration — agent relays sensitive credentials// Structured JSON logs, one object per line. Never pass secrets as fields.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Access to sensitive file pathsscripts/setup.mjs:6 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files`# Dispatch configuration. Keep this file private; see .env.example for options.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandDockerfile:22 · File permission modification command — agent changes file ownership/permissionsRUN chmod +x /usr/local/bin/entrypoint.sh && mkdir /data /backups && chown node:node /data /backupsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsscripts/setup.mjs:3 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif (!existsSync(".env.local")) {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 pathsscripts/backup.mjs:11 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesprocess.loadEnvFile(".env.local");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationlib/updates.mjs:134 · Auto-update or dynamic fetch configuration — agent may load new code at runtime// With DISPATCH_AUTO_UPDATE=true, checks every hour and applies a newer release.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈1,418 tok
1 file · 80 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

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. README directs the reader to a committed installer≈ +9 on the totalPin versions and sources; vendor anything fetched at install time.
  2. Unclaimed publisher≈ +8 on the totalClaim asmiia: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. 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.
  4. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim asmiiaPropose a patch to the maintainer