io.github.snowbikemike/tascan-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

  warn25% of grade

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

  tool "tascan_add_tasks" description: bare 'IMPORTANT:' prose in a description (tag form is high-confidence; prose is warn).

• 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.

  Reads secrets from the environment (e.g. index.js) — the recommended intake shape. 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.

  Network egress present (index.js: outbound HTTP/socket call) — expected for most servers and not a finding on its own. 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 1.0.2 (major bump): tool "tascan_update_task" gained input property(ies): response_config, required_equipment; tool "tascan_get_report" description changed (wording only, no injection pattern); tool "tascan_get_report" gained input property(ies): include_responses; new tool "tascan_reply_with_list" touches a sensitive surface (email/exec/net/fs); new tool "tascan_add_subtasks" appeared; new tool "tascan_list_subtasks" appeared; new tool "tascan_update_subtask" appeared; new tool "tascan_complete_subtask" appeared; new tool "tascan_delete_subtask" touches a sensitive surface (email/exec/net/fs); new tool "tascan_query_responses" appeared; new tool "tascan_register_tag" appeared; new tool "tascan_list_tags" appeared; new tool "tascan_get_scan_history" touches a sensitive surface (email/exec/net/fs); new tool "tascan_search_marketplace" touches a sensitive surface (email/exec/net/fs); new tool "tascan_create_zone" appeared; new tool "tascan_list_zones" appeared; new tool "tascan_update_zone" appeared; new tool "tascan_register_asset" appeared; new tool "tascan_assess_condition" touches a sensitive surface (email/exec/net/fs); new tool "tascan_condition_history" appeared; new tool "tascan_list_assets" appeared; new tool "tascan_request_payment" appeared; new tool "tascan_list_payments" appeared; new tool "tascan_get_worker_passport" touches a sensitive surface (email/exec/net/fs); new tool "tascan_server_info" appeared; new tool "tascan_find" appeared; new tool "tascan_get_worker" touches a sensitive surface (email/exec/net/fs); new tool "tascan_find_duplicate_workers" appeared; new capability primitive(s) in source: http-client; new hardcoded outbound host/BCC destination(s): github.com, tascan-live-event.netlify.app, tascan.io.

• 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://tascan-live-event.netlify.app/mcp" uses TLS (https); remote endpoint "https://app.tascan.io/mcp" uses TLS (https); remote endpoint uses OAuth (strongest auth mode)