com.52choujiang/kuaishou-insights

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 79 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.

  no resolvable repository linked to the package (provenance unverifiable)

• 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 0.1.1 (patch bump): tool "kuaishou_get_video_detail_by_url" description changed (wording only, no injection pattern); tool "kuaishou_get_video_detail_by_photo_id" description changed (wording only, no injection pattern); tool "kuaishou_submit_video_speech_text_by_video_url" description changed (wording only, no injection pattern); tool "kuaishou_submit_video_speech_text_by_photo_id" description changed (wording only, no injection pattern); tool "kuaishou_get_video_speech_text_job" description changed (wording only, no injection pattern); tool "kuaishou_get_video_comments_by_url" description changed (wording only, no injection pattern); tool "kuaishou_get_video_comment_replies_by_comment_id" description changed (wording only, no injection pattern); tool "kuaishou_search_videos" description changed (wording only, no injection pattern); tool "kuaishou_search_users" description changed (wording only, no injection pattern); new tool "socialdatax_get_points_balance" touches a sensitive surface (email/exec/net/fs).

• 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://mcp.52choujiang.com/kuaishou/mcp" uses TLS (https); remote endpoint "https://mcp.socialdatax.com/kuaishou/mcp" uses TLS (https); remote endpoint uses static token / bearer auth (acceptable)