Skills/npm/autonomad-travel

autonomad-travel@1.6.6

VERIFIED

Publisher claims: "Flights and hotels booked in one checkout; tours, events and dining to plan; group trips." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher autonomad · publishing for 197 daysInstalls 0Last detonated 13 h ago
$claude mcp add autonomad-travel -- npx -y autonomad-travel
WatchReport 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
AUTONOMAD_AGENT_CREDENTIALConfiguration, not credentials: AUTONOMAD_AGENT_DID, AUTONOMAD_AGENT_MODE, AUTONOMAD_API_URL, BOOKING_API_URL, IDENTITY_API_URL, REWARD_API_URL
Where it talks to
autonomad.ai (its own)Also clau.de — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names clau.de as well as its own vendor. The guard injects AUTONOMAD_AGENT_CREDENTIAL only into requests to autonomad.ai (and its subdomains) and refuses the rest.

$vet-skills run --secrets AUTONOMAD_AGENT_CREDENTIAL=autonomad.ai -- npx -y autonomad-travel

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 2026-11-14 and scored it 93/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 31 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
11sprocessdependency install exit 0
31sclaimed12 tools: search_hotels, search_flights, search_dining, search_activities, search_events, create_booking_intent, get_capabilities, get_updates, message_autonomad, preview_booking_change, cancel_booking, request_booking_change
31stools02bae0bdbf4863ee
31stools371b321e0e408d74
31stools8348e112ea1d4d36
31stools43cf58c3b523bb29
31stoolsfed4858658c37554
31stools188275adcb3fe494
31stools63c607129d32ff45
31stools18fd908550889755
31stoolsa8c11b04270f9ca7
31stoolsa0ea87403d8f804e
31stoolsdec0b2024685b698
31stoolsa479feb175c06a2e
31sprocessscript backend runs setup only
31sprocessno install scripts to re-run

Static findings

MEDIUM
File permission modification commanddist/server.js:34 · File permission modification command — agent changes file ownership/permissions// in ~/.autonomad/mcp-key (chmod 600). Sent as x-mcp-key on every subsequentFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

No other findings across 4,076 lines in 9 files.

Cost to the agent

Instructions loaded
≈102 tok
1 file · 9 in bundle
Tool list per prompt
≈6,285 tok
12 tools · 524 per tool
Handshake
1171 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 987

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 autonomad-travel@1.6.6 as of 12 h ago. This is the package itself, not its dependencies.