io.github.triumsebas/unlimited-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/unit/test_hosts_local.py: assigns a literal to secret (supe…23 (len 19)) — non-provider secret literal; prefer environment intake. tests/unit/test_providers_openai_compat.py: assigns a literal to api_key (my-s…ey (len 13)) — non-provider secret literal; prefer environment intake. tests/unit/test_runner_local.py: assigns a literal to secret (supe…23 (len 19)) — non-provider secret literal; prefer environment intake. Reads secrets from the environment (e.g. src/unlimited_mcp/paths.py) — the recommended intake shape.

• Permission scope

  warn15% of grade

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

  references credential paths: src/unlimited_mcp/hosts/ssh.py: references a credential path (/.ssh/) has both shell/exec and network egress — capable of download-and-run, though no such path was observed (src/unlimited_mcp/server.py: subprocess.* call; src/unlimited_mcp/providers/openai_compat.py: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (src/unlimited_mcp/server.py: subprocess.* call; src/unlimited_mcp/config/loader.py: destructive filesystem call (shutil.rmtree/os.remove/etc.)). discloses shell/exec capability: 9 files (src/unlimited_mcp/server.py, src/unlimited_mcp/server.py, src/unlimited_mcp/hosts/local.py, +6 more) discloses broad/destructive filesystem access: 10 files (src/unlimited_mcp/config/loader.py, src/unlimited_mcp/hosts/ssh.py, src/unlimited_mcp/jobs/_ts_worker.py, +7 more) Capability DISCLOSURE, not a verdict: static analysis sees the primitive is present and reachable, not whether its use is attacker-controlled.

• Version behavior

  unscannable10% of grade

  Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

  no prior version to diff (first sight of io.github.triumsebas/[email protected]); version-drift / rug-pull cannot be evaluated. Cold-start risk is covered by point-in-time checks (injection_surface, supply_chain, credential_hygiene), not here.

• 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.