Is ip-australia@0.2.1 safe to install?

ip-australia@0.2.1

VERIFIED

Publisher claims: "Enables searching Australian trade marks and registered designs, retrieving full public records for individual marks and designs, and accessing patent legal status directly from IP Australia's government registers with live, per-request results." Observed in sandbox: calls gateway.pipeworx.io only, touches nothing outside the project, writes no memory.

Registry GlamaPublisher pipeworx-io · publishing for 7 daysInstalls 0Last detonated 16 h ago

$npx skills add ip-australia

Watch Report an issue

Coverage

Server started and answered tools/list.

Tested: MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested: what the tools do when called with real credentials

Before you give it your token

It will ask for: PIPEWORX_API_KEYConfiguration, not credentials: PIPEWORX_GATEWAY_URL, PIPEWORX_META_TOOLS, PIPEWORX_TIMEOUT_MS
Where it talks to: pipeworx.io (its own)
What the honeypot saw: no credential files read · reached only gateway.pipeworx.io (its own)
What we could not test: what the tools do when called with real credentials

Connect it with a scoped credential, under the guard. It asks for PIPEWORX_API_KEY and talks to pipeworx.io. 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.

$vet-skills run --secrets PIPEWORX_API_KEY=pipeworx.io -- <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) on 2026-11-13 and scored it 85/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: calls gateway.pipeworx.io only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 20 s · 2 scenarios · 0 deviations

t+CategoryObserved action

0.0sprocessno install scripts in bundle

20snetworkCONNECT tcp://gateway.pipeworx.io:443

20sclaimed5 tools: au_search_trade_marks, au_trade_mark, au_search_designs, au_design, au_patent

20stools6b92213ef5188c1e

20stoolsb2b38da42fea45a9

20stools49e63be38df44230

20stools2a8c63215d15e9d3

20stools903716ed41c5315c

20sprocessscript backend runs setup only

20sprocessno install scripts to re-run

Static findings

MEDIUM

npx invocation of non-well-known packagebin/cli.js:2 · npx invocation of non-well-known package — may execute untrusted code// Entry point for `npx @pipeworx/mcp-<slug>` in gateway mode (bin/cli.js).Fix: Pin versions and sources; vendor anything fetched at install time.

AST06

MEDIUM

Privileged sudo command.github/workflows/publish.yml:334 · Privileged sudo command — agent may execute with elevated privilegessudo mv mcp-publisher /usr/local/bin/mcp-publisherFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

LOW

Unpinned dependency.github/workflows/publish.yml:65 · Unpinned dependencynpm install -g npm@latestFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.

AST06

Cost to the agent

Instructions loaded

≈39 tok

1 file · 9 in bundle

Tool list per prompt

≈530 tok

5 tools · 106 per tool

Handshake

1304 ms

launch to tools/list, stdio

Undocumented tools

description under 20 chars · avg 142

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

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.