Skills/npm/pilotfish-mcp-managed

pilotfish-mcp-managed@0.1.49

VERIFIED· startup only

Publisher claims: "Browser automation MCP for whole web tasks in a cloud browser: saved logins, bot checks, replays." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher gaiventures · publishing for 16 daysInstalls 9,967Last detonated 1 h ago
$claude mcp add pilotfish-mcp-managed -- npx -y @gaiventures/pilotfish-mcp-managed
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
PILOTFISH_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
PILOTFISH_TOKEN_FILEConfiguration, not credentials: PILOTFISH_KEY, PILOTFISH_URL
Where it talks to
gai.ventures (its own)
What we saw when it ran
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 with a scoped credential, under the guard. It asks for PILOTFISH_TOKEN_FILE and talks to gai.ventures. 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 --secrets PILOTFISH_TOKEN_FILE=gai.ventures -- npx -y @gaiventures/pilotfish-mcp-managed

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

What changed since 0.1.46

vet-skills diff pilotfish-mcp-managed 0.1.46 0.1.49

In the sandbox, this version reached for nothing 0.1.46 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 2026-11-21 and scored it 83/100 (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 PILOTFISH_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 · 46 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
5.5sprocessdependency install exit 0
26sfilesystemread ~/.pilotfish/mcp-managed.json outside project
26sprocessrelaunched with a decoy PILOTFISH_KEY (tagged; nothing real)
46sclaimedstartup only: exited before answering, asking for PILOTFISH_KEY (a decoy value was refused)
46sprocessscript backend runs setup only
46sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagecli.js:40 · npx invocation of non-well-known package — may execute untrusted codethrow new Error("No API key and no sign-in: set PILOTFISH_KEY, or run: npx @gaiventures/pilotfish-mcp-managed login");Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagecli.js:396 · npx invocation of non-well-known package — may execute untrusted codelog("Not signed in. Run: npx @gaiventures/pilotfish-mcp-managed login (or set PILOTFISH_KEY to an organization API key).");Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagecli.js:306 · npx invocation of non-well-known package — may execute untrusted codethrow new Error(`pilotfish ended this sign-in (${String(r.json["error_description"] ?? r.json["error"] ?? r.status)}). Run: npx @gaiventures/pilotfish-mcp-managed login`);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagecli.js:48 · npx invocation of non-well-known package — may execute untrusted code…r organization for a current one (Org settings \u2192 API keys). Signed in: run npx @gaiventures/pilotfish-mcp-managed login again."; if (/fetch failed|ECONNREFUSED|ENOTFOUND|ETIMEDOUT/i.test(m)) …Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagecli.js:368 · npx invocation of non-well-known package — may execute untrusted codesay(`Add the relay to your MCP client with: npx -y @gaiventures/pilotfish-mcp-managed`);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈68 tok
1 file · 5 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 @gaiventures/pilotfish-mcp-managed@0.1.49 as of 39 min ago. This is the package itself, not its dependencies.