dev.aicommander/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

  fail25% of grade

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

  tool "remote_exec" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "remote_job_start" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "remote_push" description: off-vendor URL in a description (aicommander.dev); 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 "@aicommander/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 1.3.0 (patch bump): new tool "remote_exec" whose description contains ignore-previous-instructions phrase; new tool "session_status" touches a sensitive surface (email/exec/net/fs); new tool "list_machines" touches a sensitive surface (email/exec/net/fs); new tool "remote_screenshot" touches a sensitive surface (email/exec/net/fs); new tool "remote_job_start" whose description contains ignore-previous-instructions phrase; new tool "remote_job_list" touches a sensitive surface (email/exec/net/fs); new tool "remote_job_status" touches a sensitive surface (email/exec/net/fs); new tool "remote_job_logs" touches a sensitive surface (email/exec/net/fs); new tool "remote_job_cancel" touches a sensitive surface (email/exec/net/fs); new tool "remote_pull" touches a sensitive surface (email/exec/net/fs); new tool "remote_push" whose description contains embedded outbound URL.

• Transport config

  pass10% of grade

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

  remote endpoint "https://aicommander.dev/mcp" uses TLS (https); remote endpoint uses OAuth (strongest auth mode)