Back to skill

Security audit

微信数据助手

Security checks for vulnerabilities and agentic risk

Overview

ClawScan’s verdict is benign with medium confidence: scanners report a WeChat content query skill with mostly purpose-aligned behavior, alongside an unpinned installer and some concerns about confirmation logging and account access.

Before installing, consider whether you are comfortable sending query details to the external service and whether the skill’s local confirmation logging and account-balance access are appropriate for your needs. The installer version is not pinned. The verdict is benign, not risk-free, and scan evidence is incomplete because some local references could not be resolved.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (16)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

Local compliance logging could be a supporting implementation detail, but this code goes beyond logging an observed event: it unconditionally sets confirmation status to confirmed. Automatically asserting legal acknowledgment is not disclosed by the declared content-query and analysis purpose. The mismatch is the unsupported confirmation assertion, not merely the local file writes or absence of API calls in this chunk.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skillhub'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The installation command executes the registry-resolved version of skillhub without pinning a reviewed release. Although this is an installer rather than an MCP server, a compromised or malicious future package release could execute code with the installing user's permissions.

Content

No source excerpt is available for this finding.

The mandatory consent gate requires Chinese-language confirmation and explicitly rejects English confirmation.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

All accepted consent phrases are Chinese, while English responses such as yes are explicitly rejected. Because execution is blocked until this gate is passed, users must confirm in Chinese regardless of their preferred language, without an opt-in or a documented justification for that language restriction.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 490)May include surrounding context.

md
| 场景 | 命令 |
|---|---|
| 查 API Key | `[ -n "${MAXHUB_API_KEY:-}" ] && echo "ok" \|\| echo "missing"` |
| 查公众号文章详情 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"url":"https://mp.weixin.qq.com/s/xxx"}' "https://www.aconfig.cn/api/v1/wechat_mp/v2/fetch_article_detail"` |
| 查文章评论 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"url":"https://mp.weixin.qq.com/s/xxx"}' "https://www.aconfig.cn/api/v1/wechat_mp/v2/fetch_article_comments"` |
| 查公众号文章列表 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"username":"gh_xxx"}' "https://www.aconfig.cn/api/v1/wechat_mp/v2/fetch_account_articles"` |
| 查视频号视频详情 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"object_id":"xxx"}' "https://www.aconfig.cn/api/v1/wechat_channels/v2/fetch_video_detail"` |

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 491)May include surrounding context.

md
|---|---|
| 查 API Key | `[ -n "${MAXHUB_API_KEY:-}" ] && echo "ok" \|\| echo "missing"` |
| 查公众号文章详情 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"url":"https://mp.weixin.qq.com/s/xxx"}' "https://www.aconfig.cn/api/v1/wechat_mp/v2/fetch_article_detail"` |
| 查文章评论 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"url":"https://mp.weixin.qq.com/s/xxx"}' "https://www.aconfig.cn/api/v1/wechat_mp/v2/fetch_article_comments"` |
| 查公众号文章列表 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"username":"gh_xxx"}' "https://www.aconfig.cn/api/v1/wechat_mp/v2/fetch_account_articles"` |
| 查视频号视频详情 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"object_id":"xxx"}' "https://www.aconfig.cn/api/v1/wechat_channels/v2/fetch_video_detail"` |
| 搜一搜 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"keyword":"AI"}' "https://www.aconfig.cn/api/

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 492)May include surrounding context.

md
| 查 API Key | `[ -n "${MAXHUB_API_KEY:-}" ] && echo "ok" \|\| echo "missing"` |
| 查公众号文章详情 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"url":"https://mp.weixin.qq.com/s/xxx"}' "https://www.aconfig.cn/api/v1/wechat_mp/v2/fetch_article_detail"` |
| 查文章评论 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"url":"https://mp.weixin.qq.com/s/xxx"}' "https://www.aconfig.cn/api/v1/wechat_mp/v2/fetch_article_comments"` |
| 查公众号文章列表 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"username":"gh_xxx"}' "https://www.aconfig.cn/api/v1/wechat_mp/v2/fetch_account_articles"` |
| 查视频号视频详情 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"object_id":"xxx"}' "https://www.aconfig.cn/api/v1/wechat_channels/v2/fetch_video_detail"` |
| 搜一搜 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"keyword":"AI"}' "https://www.aconfig.cn/api/v1/wechat_

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 493)May include surrounding context.

md
| 查公众号文章详情 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"url":"https://mp.weixin.qq.com/s/xxx"}' "https://www.aconfig.cn/api/v1/wechat_mp/v2/fetch_article_detail"` |
| 查文章评论 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"url":"https://mp.weixin.qq.com/s/xxx"}' "https://www.aconfig.cn/api/v1/wechat_mp/v2/fetch_article_comments"` |
| 查公众号文章列表 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"username":"gh_xxx"}' "https://www.aconfig.cn/api/v1/wechat_mp/v2/fetch_account_articles"` |
| 查视频号视频详情 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"object_id":"xxx"}' "https://www.aconfig.cn/api/v1/wechat_channels/v2/fetch_video_detail"` |
| 搜一搜 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"keyword":"AI"}' "https://www.aconfig.cn/api/v1/wechat_search/v2/fetch_search"` |
| 检查 SKILL 更新 | `skillhub info wechat-pro` |

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 494)May include surrounding context.

md
| 查文章评论 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"url":"https://mp.weixin.qq.com/s/xxx"}' "https://www.aconfig.cn/api/v1/wechat_mp/v2/fetch_article_comments"` |
| 查公众号文章列表 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"username":"gh_xxx"}' "https://www.aconfig.cn/api/v1/wechat_mp/v2/fetch_account_articles"` |
| 查视频号视频详情 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"object_id":"xxx"}' "https://www.aconfig.cn/api/v1/wechat_channels/v2/fetch_video_detail"` |
| 搜一搜 | `curl -X POST -H "$maxhub_auth_header" -H "Content-Type: application/json" -d '{"keyword":"AI"}' "https://www.aconfig.cn/api/v1/wechat_search/v2/fetch_search"` |
| 检查 SKILL 更新 | `skillhub info wechat-pro` |

The API workflows lack a privacy warning that user-supplied identifiers, share links, and search terms are sent to a third-party service.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The chain recipes instruct API calls rather than merely listing available tools. These calls send request parameters, including user-provided share URLs and search keywords, to https://www.aconfig.cn (L003, L008, L189–L191, L453), but the file does not warn users about this third-party disclosure; the legal warning at L058 addresses only video decryption.

Content

No source excerpt is available for this finding.

L189–L195 authorize querying the MaxHub account balance, outside the declared WeChat content-analysis purpose.

Medium
Category
Excessive Agency
Confidence
91% confidence
Finding

The whitelist permits GET /api/maxhub/balance, exposing an API-account billing capability rather than WeChat public content or analytics. Account-balance access is not declared in the manifest and is not a direct requirement of the described article, account, comment, video, or search functions.

Content

No source excerpt is available for this finding.

The API workflows lack a warning that user-provided article URLs and account identifiers are sent to a third-party service.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

These chain recipes direct API calls using article URLs and account identifiers, rather than merely listing available endpoints. The destination is aconfig.cn (L003), not WeChat, but the file does not instruct the agent to disclose that these inputs will be shared with that third party; the generic 'high' risk labels do not explain this privacy implication.

Content

No source excerpt is available for this finding.

Search workflows transmit user-provided keywords to WeChat search without a privacy disclosure.

Medium
Category
Output Handling
Confidence
87% confidence
Finding

The recipe instructs the agent to pass the user's keyword to search_wechat without warning that the query will be sent to an external service. The same undisclosed transmission occurs at L045, L070, and L095; search terms could contain private information.

Content

No source excerpt is available for this finding.

Search workflows transmit user search terms to a third-party API without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

These workflow steps instruct the agent to execute searches, sending the user's keyword to the aconfig.cn API identified at L003. Although the endpoint and request parameters are documented, the file does not warn users that their search terms will be disclosed to a third-party service; the later video-search parameter confirmation does not cover these workflows.

Content

No source excerpt is available for this finding.

Confirmation rules require Chinese-language consent without offering a language choice.

Medium
Category
Output Handling
Confidence
89% confidence
Finding

All accepted confirmation phrases are Chinese, while English affirmatives such as 'yes' are explicitly rejected. This imposes a language requirement without user opt-in; the references to Chinese compliance requirements do not explain why consent must be expressed only in Chinese.

Content

No source excerpt is available for this finding.

The unsupported-capability response mandates Chinese text without accommodating the user's language.

Low
Category
Output Handling
Confidence
92% confidence
Finding

The instruction tells the agent to reply directly with a fixed Chinese refusal when a request is unsupported. It provides no language choice or instruction to localize that response, and the WeChat-specific scope does not itself justify forcing Chinese on all users.

Content

No source excerpt is available for this finding.

Generic keywords can trigger the batch-collection warning for unrelated requests.

Low
Category
Trigger Abuse
Confidence
93% confidence
Finding

The keyword list includes everyday terms such as 全部 ('all'), 所有 ('every/all'), and 循环 ('loop'). Although the category description refers to bulk data collection, the matching rules do not require a collection-related action alongside these terms, so ordinary requests could trigger an irrelevant warning and confirmation gate.

Content

No source excerpt is available for this finding.