Skills/npm/crixin

crixin@0.7.2

VERIFIED· not started

Publisher claims: "Give your AI a real phone: place calls, send SMS, fetch recordings and transcripts. Local or hosted." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher crixin · publishing for 196 daysInstalls 0Last detonated 7d ago
$claude mcp add crixin -- npx -y crixin
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

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

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Not enough was observed to say yet. Not started: dependency install failed; the server itself was not observed. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try crixin` runs it now and prints the full answer.

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; not started: dependency install failed; the server itself was not observed) on 2026-11-07 and scored it 80/100 (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 · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.8sprocessdependency install exit 1
1.0sprocessexec /usr/bin/date
1.0sprocessexec /usr/bin/timeout
1.0sclaimedno tools/list reply (exit 0)
1.0sprocessscript backend runs setup only
1.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actiondist/cli/compare.js:36 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(row("input tokens", String(c.a.prompt_tokens), String(c.b.prompt_tokens)));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 actiondist/cli/verify.js:53 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` Anthropic API: ${r.input_tokens.toLocaleString()}`);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 actiondist/cli/report.js:39 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` Output tokens: ${fmt(r.performance.outputTokens, 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 actiondist/cli/compare.js:37 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(row("output tokens", String(c.a.output_tokens), String(c.b.output_tokens)));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Prompt injectionREADME.md:71 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file · informational: not an instruction fileCursor / VS Code: add an HTTP MCP server with the same URL and `Authorization` header. ChatGPT: Settings → Connectors → Developer mode → add the URL. The endpoint is stateless (POST only); tool names,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/cli/default.js:2 · npx invocation of non-well-known package — may execute untrusted code* Default `npx crixin` (no args) — print the voice quickstart with currentFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/cli/index.js:228 · npx invocation of non-well-known package — may execute untrusted code// -- npx -y crixin --mcp` keep working for existing wirings.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/server/views.js:1198 · npx invocation of non-well-known package — may execute untrusted codeul.innerHTML = '<li class="empty"><h3>No sessions</h3><p class="hint">Change the source filter or run <code class="mono">npx crixin ingest</code>.</p></li>';Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/cli/report.js:38 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` $ per 1K output tok: $${fmt(r.performance.costCentsPerOutputKtok / 100, 4)}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
URL with embedded credentialsdist/server/views.js:17 · URL with embedded credentials — may be phishing or credential leaking<link href="https://fonts.googleapis.com/css2?family=Geist:wght@300;400;500;600;700&family=Geist+Mono:wght@400;500&family=Instrument+Serif:ital@0;1&display=swap" rel="stylesheet" />Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
npx invocation of non-well-known packagebin/crixin.js:2 · npx invocation of non-well-known package — may execute untrusted code// npx entrypoint. Imports the compiled CLI.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/voice/mcp.js:52 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files* plain `.env` — crixin voice doesn't care.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Authorization escalation languageREADME.md:71 · Authorization escalation language · informational: not an instruction file · informational: not an instruction file · informational: not an instruction fileCursor / VS Code: add an HTTP MCP server with the same URL and `Authorization` header. ChatGPT: Settings → Connectors → Developer mode → add the URL. The endpoint is stateless (POST only); tool names,Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈97 tok
1 file · 81 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 crixin@0.7.2 as of 7d ago. This is the package itself, not its dependencies.

crixin@0.7.2 safety verdict: Verified (not started) — KillerSkills