Back to skill

Security audit

Maxhub Threads

Security checks for vulnerabilities and agentic risk

Overview

ClawScan verdict is benign with medium confidence: the findings are mainly an unpinned installation command, while the reported external API traffic is considered purpose-aligned; some reference checks were incomplete.

If you install it, consider that the installation example does not pin the `clawhub` package to a reviewed version. The scan covered all listed components, but analysis was still marked partial because some local references could not be resolved, so the evidence is incomplete. The benign verdict does not mean risk-free.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

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

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The installation example executes clawhub through npx without specifying a version, allowing the executed package to change between installations. Although this is an installer rather than an MCP server reference, a compromised package release could execute code with the installing user's privileges; the document does not establish that any compromise has occurred.

Content

No source excerpt is available for this finding.

The example invocation prompts use generic words such as “用户” (user), “搜索” (search), and “搜” (search), without requiring a Threads-specific context.

Medium
Category
Trigger Abuse
Confidence
90% confidence
Finding

These examples overlap with ordinary requests about users and searches on unrelated services. Although the README identifies the skill as a Threads assistant, it does not constrain these example invocations to Threads requests or provide exclusions.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The Chinese installation instructions likewise use npx to execute an unversioned clawhub package. This is not an MCP server reference, but it introduces a supply-chain risk: a compromised release selected during installation could execute with the user's privileges.

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/threads/{endpoint}?%7Bparams=}" \
  -H "$maxhub_auth_header"

# POST example

The example invocation phrases are generic words without a Threads-specific scope.

Low
Category
Trigger Abuse
Confidence
96% confidence
Finding

The example commands include “帖子” (post), “用户” (user), “搜索” (search), and “搜” (search), which commonly occur in unrelated requests. Although the README identifies the skill as a Threads assistant, these invocation examples do not require Threads context or provide exclusions, leaving activation scope ambiguous.

Content

No source excerpt is available for this finding.