io.github.taylorwilsdon/workspace-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

  unscannable25% of grade

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

  No tool descriptions, server instructions, prompts, or resources were fetched; nothing to scan for injection.

• Supply chain

  warn25% of grade

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

  no resolvable repository linked to the package (provenance unverifiable)

• Credential hygiene

  warn15% of grade

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

  tests/test_oauth_state_management.py: assigns a literal to token (refr…en (len 13)) — non-provider secret literal; prefer environment intake. Reads secrets from the environment (e.g. auth/credential_store.py) — the recommended intake shape.

• Permission scope

  warn15% of grade

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

  has both shell/exec and network egress — capable of download-and-run, though no such path was observed (scripts/release.py: subprocess.* call; auth/oauth_callback_server.py: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (scripts/release.py: subprocess.* call; auth/credential_store.py: open(…, 'w'/'a'/'x') write-mode file access). discloses shell/exec capability: scripts/release.py: subprocess.* call discloses broad/destructive filesystem access: 6 files (auth/credential_store.py, auth/credential_store.py, core/utils.py, +3 more) Capability DISCLOSURE, not a verdict: static analysis sees the primitive is present and reachable, not whether its use is attacker-controlled.

• 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 1.24.0 (minor bump): new capability primitive(s) in source: fs-write, http-client, net, subprocess; new hardcoded outbound host/BCC destination(s): ., accounts.google.com, console, console.cloud.google.com, docs.google.com, drive.google.com, example.com, github.com, github.dev, googleapis.github.io, localhost-test, mail.google.com, my-custom-redirect.uri, oauth2.googleapis.com, openidconnect.googleapis.com, schemas.openxmlformats.org, script.google.com, token, vscode.dev, workspacemcp.com, www.googleapis.com.

• Transport config

  warn10% of grade

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

  manifest/source references tracking behavior — disclosure