Back to skill

Security audit

Maxhub Wechat

Security checks for vulnerabilities and agentic risk

Overview

ClawScan labels this skill suspicious with medium confidence because it found concerns about sending broad or unclear searches to MaxHub and using an unpinned installer; the evidence is incomplete because Skillspector reported partial analysis.

Review the skill's instructions and decide whether you are comfortable with queries being sent to MaxHub, especially when requests are ambiguous or sensitive. If you install it, use a reviewed, fixed version of the installer and skill where available. Treat the verdict as a caution: Skillspector's analysis was partial because some local references could not be resolved, and the scans do not establish that the skill is safe.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

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

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The documented installation command executes an unpinned npm package through npx, allowing the code executed during installation to change without review. Although clawhub is an installer rather than an MCP server, a compromised future release could execute code with the installing user's permissions.

Content

No source excerpt is available for this finding.

Example invocation prompts include generic terms for videos and articles without a WeChat-specific constraint.

Medium
Category
Trigger Abuse
Confidence
94% confidence
Finding

The example prompts include “视频” (video) and “文章” (article), which commonly occur in requests unrelated to WeChat. Although the README describes a WeChat assistant, these invocation examples provide no exclusions or explicit requirement for WeChat context and could lead to unintended activation.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The installation example uses npx without fixing the clawhub package version, so subsequent installations can execute different, unreviewed code. This is a supply-chain exposure rather than an MCP-server configuration issue; exploitation would require a compromised or malicious resolved package.

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 53)May include surrounding context.

md
maxhub_auth_header="Authorization: Bearer ${MAXHUB_API_KEY}"

# GET example
curl -s "https://www.aconfig.cn/api/v1/wechat/{endpoint}?%7Bparams=}" \
  -H "$maxhub_auth_header"

# POST example

The query workflow lacks a privacy warning about sending user-supplied query data to MaxHub.

Medium
Category
Output Handling
Confidence
86% confidence
Finding

The routing rules accept broad signals such as 'search' and 'user', default uncertain requests to Channels, and subsequently direct autonomous API execution without a privacy or sensitive-query check. This combination can send ambiguous or sensitive user-supplied search terms to MaxHub without establishing that the user intended an external WeChat lookup; naming the provider in the skill documentation does not resolve that ambiguity.

Content

No source excerpt is available for this finding.

The example invocation phrases include generic words for “video” and “article,” which do not uniquely indicate a WeChat data request.

Low
Category
Trigger Abuse
Confidence
92% confidence
Finding

The usage table presents “视频” (video) and “文章” (article) as example commands without requiring a WeChat-specific qualifier. These everyday terms could cause unintended activation for unrelated video or article requests, and no exclusion conditions are provided.

Content

No source excerpt is available for this finding.