io.github.microsoft/playwright-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 "browser_drop" param "data" description: off-vendor URL in a description (example.com); capability text should not name where data goes.

• Supply chain

  warn25% of grade

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

  package name "@playwright/mcp" is edit-distance 2 from popular package "yup" (typosquat candidate)

• 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 0.0.78 (patch bump): new tool "browser_close" appeared; new tool "browser_resize" appeared; new tool "browser_console_messages" appeared; new tool "browser_handle_dialog" appeared; new tool "browser_evaluate" appeared; new tool "browser_file_upload" touches a sensitive surface (email/exec/net/fs); new tool "browser_drop" appeared; new tool "browser_find" appeared; new tool "browser_fill_form" appeared; new tool "browser_press_key" touches a sensitive surface (email/exec/net/fs); new tool "browser_type" appeared; new tool "browser_navigate" touches a sensitive surface (email/exec/net/fs); new tool "browser_navigate_back" appeared; new tool "browser_network_requests" appeared; new tool "browser_network_request" appeared; new tool "browser_run_code_unsafe" touches a sensitive surface (email/exec/net/fs); new tool "browser_take_screenshot" appeared; new tool "browser_snapshot" appeared; new tool "browser_click" appeared; new tool "browser_drag" appeared; new tool "browser_hover" appeared; new tool "browser_select_option" appeared; new tool "browser_tabs" appeared; new tool "browser_wait_for" appeared.

• 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.