MCP server · trust report

com.52choujiang/wechat-channels-insights

1 check that ran failed — version behavior — so this release can’t be trusted as-is.

Publisher
com.52choujiang
Repository
Install
remote only
Versions
2
MCP revision
2025-11-25 · superseded
Inspected
5 of 6 checks · 85%
Scored
2026-09-04 · rubric 1.0.0

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.

6 checks2 clean3 flagged1 not inspected
  • Injection surface

    warn25% of grade

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

    tool "wechat_get_user_info_by_url" param "url" description: off-vendor URL in a description (weixin.qq.com); capability text should not name where data goes. tool "wechat_get_user_posted_videos_by_url" param "url" description: off-vendor URL in a description (weixin.qq.com); capability text should not name where data goes. tool "wechat_get_video_comments_by_url" param "url" description: off-vendor URL in a description (weixin.qq.com); capability text should not name where data goes. tool "wechat_get_mp_article_detail_by_url" param "url" description: off-vendor URL in a description (mp.weixin.qq.com); capability text should not name where data goes. tool "wechat_get_video_detail_by_url" param "url" description: off-vendor URL in a description (weixin.qq.com); capability text should not name where data goes. tool "wechat_submit_video_speech_text_by_video_url" param "video_url" description: off-vendor URL in a description (weixin.qq.com); capability text should not name where data goes.

  • 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 "wechat_get_user_info_by_user_id" description changed (wording only, no injection pattern); tool "wechat_get_user_info_by_url" description changed (wording only, no injection pattern); tool "wechat_get_user_posted_videos_by_user_id" description changed (wording only, no injection pattern); tool "wechat_get_user_posted_videos_by_url" description changed (wording only, no injection pattern); tool "wechat_get_video_comment_replies_by_comment_id" description changed (wording only, no injection pattern); tool "wechat_get_video_comments_by_object_id" description changed (wording only, no injection pattern); tool "wechat_get_video_detail_by_encrypted_object_id" description changed (wording only, no injection pattern); tool "wechat_get_video_detail_by_url" description changed (wording only, no injection pattern); tool "wechat_submit_video_speech_text_by_video_url" description changed (wording only, no injection pattern); tool "wechat_submit_video_speech_text_by_encrypted_object_id" description changed (wording only, no injection pattern); tool "wechat_get_video_speech_text_job" description changed (wording only, no injection pattern); tool "wechat_search_videos" 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/wechat/mcp" uses TLS (https); remote endpoint "https://mcp.socialdatax.com/wechat/mcp" uses TLS (https); remote endpoint uses static token / bearer auth (acceptable)

Version history

Each release plotted by grade against the safe line at B. A version that sinks below the line has lost its trusted standing — the shape of a rug-pull.

VersionPublishedGradeScoreInspectedChange
v0.1.2 · current2026-08-04 C655/6 · 85%±0
v0.1.12026-06-22 C654/6 · 75%