Skills/Glama/message-cp

message-cp@0.2.0

CAUTION· install only

Publisher claims: "An MCP server that lets AI agents register a name and bio, discover one another, exchange messages, and be woken when mail arrives rather than polling, backed by a shared SQLite database over stdio for one machine or HTTP for a team." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher colinhallett · publishing for 2 daysInstalls 0Last detonated 2d ago
What would fix thisWatchDispute verdict

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: 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
LIVE_SIGNIN_TOKENMESSAGE_CP_HTTP_TOKENConfiguration, not credentials: MAX_KEY_LENGTH, MESSAGE_CP_AGENT_KEY
Where it talks to
no vendor host named in the code
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. It asks for LIVE_SIGNIN_TOKEN, MESSAGE_CP_HTTP_TOKEN and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$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 2026-11-12 and scored it 65/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; Privileged sudo command; Instructs the agent to modify its persistent memory or instruction files. 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

CRITICAL
HTML comment carrying imperative instructions to the agenttessl-factory/skills/tune-review-lenses/SKILL.md:67 · HTML comment carrying imperative instructions to the agenttessl-code-review:run:v1Fix: 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/init.ts:559 · npx invocation of non-well-known package — may execute untrusted code* The stdio server of the package running `init`: `npx -y message-cp` resolves only once the package is published.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/init.ts:58 · npx invocation of non-well-known package — may execute untrusted codeexport const MANUAL_ADD = "claude mcp add message-cp -- npx -y message-cp";Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Privileged sudo commandtessl-factory/skills/vm-check/SKILL.md:5 · Privileged sudo command — agent may execute with elevated privilegesreport the OS, resources, virtualisation, tools, sudo and Docker, andFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Instructs the agent to modify its persistent memory or instruction files.tessl/plugins/tessl-labs/factory-setup/skills/check-cloud-setup/SKILL.md:15 · Instructs the agent to modify its persistent memory or instruction filescan write files the branch also adds, such as `AGENTS.md` and `CLAUDE.md`.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/init.ts:446 · npx invocation of non-well-known package — may execute untrusted code/** Whether `get`'s output describes a stdio server that runs `npx -y message-cp`. */Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandsrc/init.ts:189 · File permission modification command — agent changes file ownership/permissions…ile message-cp init was running; it was left as it is. To make it private, run: chmod 600 ${shellQuote(file)}, then run message-cp init again.`); } chmodS…Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagetessl-factory/skills/release-notes/SKILL.md:70 · npx invocation of non-well-known package — may execute untrusted code`npx -y message-cp init`, or `npm install -g message-cp@<version>`.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandsrc/wait.ts:112 · File permission modification command — agent changes file ownership/permissions…TokenFile(publicUrl, account, name)}, privately: mkdir -p ~/.message-cp/wait && chmod 700 ~/.message-cp ~/.message-cp/wait, then rm -f ${file} && (umask 077 && printf…Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/init.ts:33 · npx invocation of non-well-known package — may execute untrusted code// `message-cp init`: adds the stdio server `npx -y message-cp` to one coding agent's user-level MCP configuration onFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandscripts/e2e.mjs:94 · Process kill command — agent can terminate processesconst kill = setTimeout(() => child.kill("SIGKILL"), 5000);Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandsrc/init.ts:264 · File permission modification command — agent changes file ownership/permissions… 0o777).toString(8).padStart(4, "0")} is wider than 0600; make it private with: chmod 600 ${shellQuote(file)}, then run message-cp init again`); } if (st.size…Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandsrc/init.ts:175 · File permission modification command — agent changes file ownership/permissions…ers of this machine can read it; it was left as it is. To make it private, run: chmod 600 ${shellQuote(file)}, then run message-cp init again.`); } return ser…Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file paths.tessl/plugins/tessl-labs/factory-setup/skills/prepare-repo/scripts/score-repo.mjs:923 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files… for (const m of repo .read(f) .matchAll( /process\.env\.([A-Z][A-Z0-9_]+)|process\.env\[['"]([A-Z][A-Z0-9_]+)|os\.environ(?:\.get)?\(?…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)src/connect.ts:99 · MCP server using network transport (SSE/HTTP) — data sent over networkconst json = JSON.stringify({ mcpServers: { "message-cp": { type: "http", url: endpoint.href, headers } } }, null, 2);Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
File type combined with upload actiontessl-factory/skills/tune-review-lenses/SKILL.md:47 · File type combined with upload action — agent may exfiltrate local data files…iled; record the gap in the report. ## What to read Read `.cloud-launch/inputs.json` and require UUID `orgId` and `projectId`. Get the current UTC time with a tool. Look back 14 days; an optional `lookbackDays` input (integer 1 to 60) repl…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/init.ts:146 · npx invocation of non-well-known package — may execute untrusted code* `npx -y message-cp`), "differs" otherwise. Refuses, changing nothing, a file that is not a JSON object or whoseFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file paths.tessl/plugins/tessl-labs/factory-setup/skills/prepare-repo/scripts/score-repo.mjs:947 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files`reads ${names.size} environment variables but has no .env template`,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiontessl-factory/skills/tune-review-lenses/SKILL.md:108 · File type combined with upload action — agent may exfiltrate local data files…ded, with why; and every read that failed or was capped. 2. Write `launch-result.json` at the clone root. Use `status: succeeded` with a `summary` of two to four plain sentences: the window, how many pull requests and Code Review findings …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Refusal suppressiontessl-factory/skills/pr-shepherd-session/SKILL.md:217 · Refusal suppression — attempting to prevent safety responses7. A red check, a failing test or a broken build is never declined. Before youFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Destructive file system command detectedtessl-factory/skills/vm-check/SKILL.md:24 · Destructive file system command detected`rm -rf /var/tmp/vmcheck && cp -r . /var/tmp/vmcheck && cd /var/tmp/vmcheckFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandtessl-factory/skills/vm-check/SKILL.md:21 · Privileged sudo command — agent may execute with elevated privileges`sudo -n true && echo sudo-ok || echo no-sudo`;Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandsrc/init.ts:504 · File permission modification command — agent changes file ownership/permissionsreturn `${file} would hold the token, and other users of this machine can read it; to make it private, run: chmod 600 ${shellQuote(file)}, then run message-cp init again.`;Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file paths.tessl/plugins/tessl-labs/factory-setup/skills/prepare-repo/scripts/score-repo.mjs:942 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files/(^|\/)(\.env\.(example|sample|template|dist|defaults)|example\.env|env\.example)$/,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈42,285 tok
26 files · 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

15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim colinhallett: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. 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.
  5. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  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 colinhallettPropose a patch to the maintainer