io.github.alexanderolvera/dfhack-mcp

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

  pass25% of grade

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

  Scanned 122 text field(s); no instruction-injection patterns found. PASS = no static red flag. A server can serve different tool descriptions at runtime (the rug-pull class), which static scanning cannot see.

• Supply chain

  warn25% of grade

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

  install hook "prepare" present and not a recognized benign build command

• 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 1.4.0 (patch bump): new tool "artifacts_and_engravings" touches a sensitive surface (email/exec/net/fs); new tool "burrows" appeared; new tool "chronicle" touches a sensitive surface (email/exec/net/fs); new tool "citizen" appeared; new tool "defenses" appeared; new tool "environment" appeared; new tool "farming" appeared; new tool "find_unit" appeared; new tool "fluids" touches a sensitive surface (email/exec/net/fs); new tool "fort_health" touches a sensitive surface (email/exec/net/fs); new tool "fort_status" appeared; new tool "game_data" appeared; new tool "geology" appeared; new tool "hauling_routes" touches a sensitive surface (email/exec/net/fs); new tool "identify" appeared; new tool "injuries_and_health" appeared; new tool "jobs_and_labor" appeared; new tool "livestock_and_pastures" appeared; new tool "map_overview" touches a sensitive surface (email/exec/net/fs); new tool "mandates_and_justice" appeared; new tool "mechanisms" appeared; new tool "military" touches a sensitive surface (email/exec/net/fs); new tool "moods" appeared; new tool "nobles_and_administrators" appeared; new tool "petitions" appeared; new tool "rooms_and_zones" appeared; new tool "site_history" appeared; new tool "stockpiles" appeared; new tool "stocks" appeared; new tool "threats" appeared; new tool "tile_region" touches a sensitive surface (email/exec/net/fs); new tool "trade" appeared; new tool "unmet_needs" appeared; new tool "wiki_lookup" touches a sensitive surface (email/exec/net/fs); new tool "wiki_search" touches a sensitive surface (email/exec/net/fs); new tool "work_details" touches a sensitive surface (email/exec/net/fs); new tool "work_order_list" touches a sensitive surface (email/exec/net/fs).

• Transport config

  unscannable10% of grade

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

  local stdio server: no remote transport or auth surface, and no phone-home/telemetry signal found in source. Absence of transport findings is NOT a safety guarantee — phone-home hosts can be constructed at runtime and defeat static analysis.