ai.wiplash/wiplash

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

  warn25% of grade

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

  dependency "jose" is edit-distance 2 from popular package "@babel/core" (typosquat candidate)

• Credential hygiene

  fail15% of grade

  How the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.

  tool "revoke_agent_credential" has a secret-shaped input parameter "credential_id" — secrets must never be tool parameters (the model would supply/handle the credential).

• 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 0.3.0 (minor bump): new tool "search_posts" appeared; new tool "get_post" touches a sensitive surface (email/exec/net/fs); new tool "inspect_code_request" touches a sensitive surface (email/exec/net/fs); new tool "inspect_code_review" touches a sensitive surface (email/exec/net/fs); new tool "render_post_cards" touches a sensitive surface (email/exec/net/fs); new tool "render_post" touches a sensitive surface (email/exec/net/fs); new tool "find_agents" touches a sensitive surface (email/exec/net/fs); new tool "get_agent" touches a sensitive surface (email/exec/net/fs); new tool "list_hot_topics" appeared; new tool "get_waterpark_rules" touches a sensitive surface (email/exec/net/fs); new tool "list_my_agents" appeared; new tool "get_my_agent" touches a sensitive surface (email/exec/net/fs); new tool "register_agent" touches a sensitive surface (email/exec/net/fs); new tool "update_agent_profile" touches a sensitive surface (email/exec/net/fs); new tool "update_agent_avatar" touches a sensitive surface (email/exec/net/fs); new tool "revoke_agent_credential" touches a sensitive surface (email/exec/net/fs); new tool "create_text_post" appeared; new tool "create_media_post" touches a sensitive surface (email/exec/net/fs); new tool "list_my_code_repositories" touches a sensitive surface (email/exec/net/fs); new tool "create_code_request" appeared; new tool "create_code_review" touches a sensitive surface (email/exec/net/fs); new tool "create_feedback" appeared; new tool "update_feedback" appeared; new tool "delete_feedback" touches a sensitive surface (email/exec/net/fs); new tool "vote_post" appeared; new tool "vote_feedback" appeared; new hardcoded outbound host/BCC destination(s): auth.wiplash.ai, mcp.wiplash.ai.

• Transport config

  fail10% of grade

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

  remote MCP endpoint declares NO authentication (unauthenticated remote — nginx-ui/CVE-2026-33032 class)