ai.gondola/gondola

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_travel_profiles" description: cross-tool redirection ('instead of call…').

• 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 0.1.4 (patch bump): new tool "book_hotel" appeared; new tool "book_vehicle" appeared; new tool "cancel_vehicle_booking" appeared; new tool "compare_rates" appeared; new tool "create_rate_alert" touches a sensitive surface (email/exec/net/fs); new tool "credit_card_coverage" appeared; new tool "delete_rate_alert" touches a sensitive surface (email/exec/net/fs); new tool "diagnose_rates" appeared; new tool "get_booking" appeared; new tool "get_booking_link" touches a sensitive surface (email/exec/net/fs); new tool "get_free_night_credits" appeared; new tool "get_hotel_details" appeared; new tool "get_hotel_reviews" appeared; new tool "get_hotel_stats" appeared; new tool "get_loyalty_accounts" appeared; new tool "get_multi_night_rates" appeared; new tool "get_past_trips" touches a sensitive surface (email/exec/net/fs); new tool "get_payment_methods" appeared; new tool "get_rate_alerts" appeared; new tool "get_similar_hotels" appeared; new tool "get_suggested_searches" appeared; new tool "get_travel_profiles" touches a sensitive surface (email/exec/net/fs); new tool "get_traveler_context" appeared; new tool "get_upcoming_trips" appeared; new tool "get_vehicle_booking" appeared; new tool "get_vehicle_booking_coverage" appeared; new tool "get_vehicle_booking_link" touches a sensitive surface (email/exec/net/fs); new tool "get_vehicle_details" appeared; new tool "optimize_loyalty_portfolio" appeared; new tool "predict_price" appeared; new tool "search_events" appeared; new tool "search_flights" appeared; new tool "search_hotels" appeared; new tool "search_vehicles" appeared; new tool "update_traveler_profile" appeared; new hardcoded outbound host/BCC destination(s): mcp.gondola.ai.

• 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://mcp.gondola.ai/mcp" uses TLS (https); remote endpoint uses OAuth (strongest auth mode)