io.github.BourbonDog/amicus

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.

  install hook "postinstall" present and not a recognized benign build command

• 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/utils/abort-coordinator.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

  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 (src/sidecar/electron-install.js: imports child_process and calls exec/spawn; electron/summary.js: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (src/sidecar/electron-install.js: imports child_process and calls exec/spawn; src/utils/api-key-store.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename)). discloses shell/exec capability: 9 files (src/sidecar/electron-install.js, src/sidecar/interactive.js, src/mcp-server.js, +6 more) discloses broad/destructive filesystem access: 25 files (src/utils/api-key-store.js, src/utils/atomic-write.js, src/utils/auth-json.js, +22 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 4.9.2 (patch bump): new capability primitive(s) in source: child_process, fs-write, http-client; new hardcoded outbound host/BCC destination(s): ..., aistudio.google.com, api.anthropic.com, api.deepseek.com, api.openai.com, bourbondog.github.io, console.anthropic.com, generativelanguage.googleapis.com, github.com, nodejs.org, opencode.ai, openrouter.ai, platform.deepseek.com, platform.openai.com, www.w3.org.

• Transport config

  fail10% of grade

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

  source performs runtime self-update / download-and-execute (bypasses version_behavior); manifest/source references tracking behavior — disclosure