com.voyagehacks/travel

What we checked

Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.

• Injection surface

  warn25% of grade

  Tool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).

  tool "get_article" param "url" description: off-vendor URL in a description (voyagehacks.com); capability text should not name where data goes.

• Supply chain

  pass25% of grade

  Package provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.

  repository linkage verified

• Credential hygiene

  pass15% of grade

  How the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.

  No hardcoded secrets, secret-shaped tool parameters, or leaked keys found. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

• Permission scope

  pass15% of grade

  Declared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.

  No shell-exec, unbounded/sensitive filesystem, or download-and-run primitives found in scanned source. PASS = no static red flag. Static scanning is blind to code fetched or executed at runtime.

• Version behavior

  fail10% of grade

  Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

  vs prior 2.0.0 (minor bump): tool "search_articles" description changed (wording only, no injection pattern); tool "search_articles" gained input property(ies): section; tool "get_article" description changed (wording only, no injection pattern); tool "search_travel_gear" description changed (wording only, no injection pattern); tool "recommend_travel_gear" description changed (wording only, no injection pattern); tool "recommend_travel_gear" gained input property(ies): destination, trip_length_days, season, activities, luggage, traveler_type, budget; tool "get_flight_links" description changed (wording only, no injection pattern); tool "get_hotel_links" description changed (wording only, no injection pattern); tool "get_hotel_links" gained input property(ies): children; tool "get_car_rental_links" description changed (wording only, no injection pattern); tool "get_airport_transfer_links" description changed (wording only, no injection pattern); tool "get_esim_links" description changed (wording only, no injection pattern); tool "get_travel_vpn_links" description changed (wording only, no injection pattern); tool "get_credit_card_links" description changed (wording only, no injection pattern); tool "get_booking_links" description changed (wording only, no injection pattern); tool "get_booking_links" gained input property(ies): depart_date, return_date, adults, include, lang; new hardcoded outbound host/BCC destination(s): github.com, voyagehacks.com.

• Transport config

  pass10% of grade

  Remote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.

  remote endpoint "https://voyagehacks.com/mcp" uses TLS (https); remote endpoint uses OAuth (strongest auth mode)