io.linklore/llre

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

  pass25% of grade

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

  Scanned 347 text field(s); no instruction-injection patterns found. PASS = no static red flag. A server can serve different tool descriptions at runtime (the rug-pull class), which static scanning cannot see.

• Supply chain

  warn25% of grade

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

  package name "llre" is edit-distance 2 from popular package "xlrd" (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

  unscannable15% of grade

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

  No source files, package.json, or pyproject were fetched; cannot infer capability scope.

• 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 0.2.1 (patch bump): tool "config" description changed (wording only, no injection pattern); tool "doc_rollup" description changed (wording only, no injection pattern); tool "show" description changed (wording only, no injection pattern); tool "show" gained input property(ies): section; tool "openbox" description changed (wording only, no injection pattern); tool "push" description changed (wording only, no injection pattern); tool "pull" description changed (wording only, no injection pattern); tool "add" description changed (wording only, no injection pattern); tool "edit" description changed (wording only, no injection pattern); tool "edit" gained input property(ies): auto_search; tool "rm" description changed (wording only, no injection pattern); tool "restore" gained input property(ies): max; tool "log" description changed (wording only, no injection pattern); new tool "forced" appeared; new tool "local_cross" touches a sensitive surface (email/exec/net/fs); new tool "market" appeared.

• 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.