io.github.ivanostanin/lucius-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

  fail25% of grade

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

  Python build script executes at build time: network call in build script

• 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. src/cli/completion_installer.py) — the recommended intake shape. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

• Permission scope

  warn15% of grade

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

  discloses broad/destructive filesystem access: deployment/scripts/build-mcpb.sh: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: deployment/scripts/build-mcpb.sh: path traversal ('../') combined with file access discloses broad/destructive filesystem access: deployment/scripts/build_all_cli.sh: path traversal ('../') combined with file access discloses broad/destructive filesystem access: deployment/scripts/build_cli_unix.sh: path traversal ('../') combined with file access discloses broad/destructive filesystem access: scripts/build_tool_schema.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: scripts/filter_openapi.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: src/cli/auth_config.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/client/generated/api_client.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: src/client/generated/api_client.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) Capability DISCLOSURE, not a verdict: static analysis sees the primitive is present and reachable, not whether its use is attacker-controlled.

• Version behavior

  pass10% of grade

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

  tool surface, capabilities, install scripts, and publisher unchanged vs prior version 0.12.2 (patch bump); no rug-pull drift.

• 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 analytics behavior — disclosure