io.github.Cloto-dev/cpersona

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 224 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

  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.

  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 2.5.2 (patch bump): new tool "pause_persistence" touches a sensitive surface (email/exec/net/fs); new tool "resume_persistence" touches a sensitive surface (email/exec/net/fs); new tool "persistence_status" touches a sensitive surface (email/exec/net/fs); new tool "get_operating_context" touches a sensitive surface (email/exec/net/fs); new tool "store" touches a sensitive surface (email/exec/net/fs); new tool "recall" appeared; new tool "recall_with_context" appeared; new tool "get_contents" touches a sensitive surface (email/exec/net/fs); new tool "get_profile" appeared; new tool "update_profile" appeared; new tool "archive_episode" appeared; new tool "list_memories" appeared; new tool "list_episodes" appeared; new tool "delete_agent_data" touches a sensitive surface (email/exec/net/fs); new tool "calibrate_threshold" appeared; new tool "set_recall_precision" appeared; new tool "get_recall_precision" touches a sensitive surface (email/exec/net/fs); new tool "delete_memory" touches a sensitive surface (email/exec/net/fs); new tool "delete_episode" touches a sensitive surface (email/exec/net/fs); new tool "update_memory" appeared; new tool "lock_memory" appeared; new tool "unlock_memory" appeared; new tool "get_queue_status" appeared; new tool "export_memories" touches a sensitive surface (email/exec/net/fs); new tool "import_memories" touches a sensitive surface (email/exec/net/fs); new tool "merge_memories" appeared; new tool "check_health" touches a sensitive surface (email/exec/net/fs); new tool "deep_check" touches a sensitive surface (email/exec/net/fs); new tool "migrate_channel_axis" touches a sensitive surface (email/exec/net/fs).

• 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.