Skills/npm/ziggs-mcp

ziggs-mcp@0.43.17

VERIFIED· startup only

Publisher claims: "MCP server for Claude Code, Cursor, and other MCP hosts — act as your Ziggs delegate agent" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher ziggs-ai · publishing for 160 daysInstalls 15,076Last detonated 9 h ago
$claude mcp add ziggs-mcp -- npx -y @ziggs-ai/ziggs-mcp
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials
Needs
ZIGGS_OPERATOR_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

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
no credential variables read in the code; at startup it asked for ZIGGS_OPERATOR_KEY
Where it talks to
ziggsai.com (its own)
What the honeypot saw
no credential files read · no network
What we could not test
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it under the guard. Startup only; authenticated tool behavior not tested. The code names no credential variable and talks to ziggsai.com, its own; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- npx -y @ziggs-ai/ziggs-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 0.41.11

vet-skills diff ziggs-mcp 0.41.11 0.43.17

In the sandbox, this version reached for nothing 0.41.11 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-18 and scored it 86/100 (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 (it asks for ZIGGS_OPERATOR_KEY); 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 · 47 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
7.1sprocessdependency install exit 0
27sprocessrelaunched with a decoy ZIGGS_OPERATOR_KEY (tagged; nothing real)
47sclaimedstartup only: exited before answering, asking for ZIGGS_OPERATOR_KEY (a decoy value was refused)
47sprocessscript backend runs setup only
47sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsdist/config.js:108 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// HTTP_URL inside resolveDelegateCreds, so a dev checkout's .env cannotFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectionexamples/chatgpt-remote-oauth.md:92 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…Fix | |---------|--------------|-----| | No option to add a custom MCP server | Developer mode off, or the plan does not include custom MCP | Turn on developer mode (Settings…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionexamples/chatgpt-remote-oauth.md:46 · Prompt injection — known jailbreak technique reference · informational: not an instruction file1. Turn developer mode on. On an individual account: **Settings → Security andFix: 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/config.js:29 · npx invocation of non-well-known package — may execute untrusted code* one-minute task starting `npx @ziggs-ai/ziggs-mcp` — is a new host everyFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Authorization escalation languageexamples/chatgpt-remote-oauth.md:21 · Authorization escalation language · informational: not an instruction file| Plus | developer mode; write support not stated on both of OpenAI's pages | assume read-only until you see otherwise |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionexamples/chatgpt-remote-oauth.md:20 · Prompt injection — known jailbreak technique reference · informational: not an instruction file| Pro | developer mode, read/fetch only | the read tools |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageREADME.md:62 · Authorization escalation language · informational: not an instruction file…ness / Enterprise / Edu get the write tools (beta); Pro gets read/fetch only in developer mode, and Plus is not stated consistently by OpenAI, so treat it as read-only. Web o…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionexamples/chatgpt-remote-oauth.md:21 · Prompt injection — known jailbreak technique reference · informational: not an instruction file| Plus | developer mode; write support not stated on both of OpenAI's pages | assume read-only until you see otherwise |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionexamples/chatgpt-remote-oauth.md:47 · Prompt injection — known jailbreak technique reference · informational: not an instruction filelogin → Developer mode**. On a workspace plan this is an admin setting ratherFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageREADME.md:77 · Authorization escalation language · informational: not an instruction file| ChatGPT | remote OAuth (custom MCP app, developer mode) | yes, 2026-08-13: writes need a Business/Enterprise/Edu plan |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageexamples/chatgpt-remote-oauth.md:47 · Authorization escalation language · informational: not an instruction filelogin → Developer mode**. On a workspace plan this is an admin setting ratherFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageexamples/chatgpt-remote-oauth.md:92 · Authorization escalation language · informational: not an instruction file…Fix | |---------|--------------|-----| | No option to add a custom MCP server | Developer mode off, or the plan does not include custom MCP | Turn on developer mode (Settings…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 packagedist/config.d.ts:27 · npx invocation of non-well-known package — may execute untrusted code* one-minute task starting `npx @ziggs-ai/ziggs-mcp` — is a new host everyFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandpackage.json:38 · File permission modification command — agent changes file ownership/permissions"build": "tsc -p tsconfig.json && chmod +x dist/index.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Authorization escalation languageexamples/chatgpt-remote-oauth.md:20 · Authorization escalation language · informational: not an instruction file| Pro | developer mode, read/fetch only | the read tools |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionREADME.md:77 · Prompt injection — known jailbreak technique reference · informational: not an instruction file| ChatGPT | remote OAuth (custom MCP app, developer mode) | yes, 2026-08-13: writes need a Business/Enterprise/Edu plan |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:62 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…ness / Enterprise / Edu get the write tools (beta); Pro gets read/fetch only in developer mode, and Plus is not stated consistently by OpenAI, so treat it as read-only. Web o…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageexamples/chatgpt-remote-oauth.md:46 · Authorization escalation language · informational: not an instruction file1. Turn developer mode on. On an individual account: **Settings → Security andFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈4,674 tok
1 file · 80 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 @ziggs-ai/ziggs-mcp@0.43.17 as of 8 h ago. This is the package itself, not its dependencies.