io.github.TotesMagotes/mcp-server-auth

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 "send_report_to_accounting" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "fix_compliance" description: off-vendor URL in a description (www.expensebot.ai); capability text should not name where data goes. tool "update_expense" description: off-vendor URL in a description (www.expensebot.ai); capability text should not name where data goes. tool "correct_expenses" description: off-vendor URL in a description (www.expensebot.ai); capability text should not name where data goes.

• Supply chain

  pass25% of grade

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

  repository linkage verified

• 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/client.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/test.js: imports child_process and calls exec/spawn; src/client.js: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (src/test.js: imports child_process and calls exec/spawn; scripts/generate-descriptions-from-kb.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename)). discloses shell/exec capability: src/test.js: imports child_process and calls exec/spawn discloses broad/destructive filesystem access: scripts/generate-descriptions-from-kb.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/generate-descriptions-from-kb.js: builds a path containing '..' (traversal-prone) 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 0.6.22 (patch bump): tool "fix_compliance" description changed and now contains embedded outbound URL; tool "fix_compliance" gained input property(ies): change, selection, operationId, confirm, status, undo; tool "add_income" description changed (wording only, no injection pattern); tool "update_expense" description changed and now contains embedded outbound URL; new capability primitive(s) in source: child_process, fs-write, http-client; new hardcoded outbound host/BCC destination(s): 127.0.0.1, github.com, www.expensebot.ai.

• 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