pilotfish-mcp-managed@0.1.46
VERIFIED· startup onlyPublisher claims: "Whole browser tasks done in pilotfish's cloud for any MCP agent, signed in with your saved logins. mcprush.com-37c48d491684ec6011385ea5" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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 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 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.
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; startup only; authenticated tool behavior not tested) on 2026-11-18 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 (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 · 45 s · 2 scenariosStatic findings
…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.throw 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.say(`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.log("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.throw 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.Cost to the agent
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@0.1.46 as of 6 h ago. This is the package itself, not its dependencies.