Back to skill

Security audit

Maxhub Twitter

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign because the reported activity appears aligned with its purpose, while noting an unpinned installer command and incomplete analysis.

The verdict is benign, not a guarantee of safety, and confidence is medium. Before installing, consider that the installer command is unpinned and that the skill sends API requests to an external service; avoid including confidential search terms. Some references could not be resolved, so the scan evidence is incomplete.

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
89% confidence
Finding

The installation command can download and execute an unpinned version of clawhub, exposing users to compromised or unexpectedly changed package releases with their local privileges. This is a supply-chain weakness in installation guidance, although the referenced command is a CLI installer rather than an MCP server.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
89% confidence
Finding

The installation instructions use npx without fixing the clawhub package version, permitting execution of a changed or compromised release with the installing user's privileges. The underlying supply-chain concern is valid, but identifying this CLI command as an MCP server is inaccurate.

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

# POST example

The query workflow lacks a privacy warning that user-supplied search terms and target identifiers are sent to MaxHub.

Medium
Category
Output Handling
Confidence
89% confidence
Finding

The workflow instructs the agent to search for users and retrieve profiles and posts autonomously through a third-party API. Although the file names the provider and describes the queries as read-only, it does not warn that user-supplied search terms, account identifiers, or potentially sensitive monitoring interests are disclosed to that provider.

Content

No source excerpt is available for this finding.

Usage examples include generic prompts without Twitter/X-specific activation constraints.

Low
Category
Trigger Abuse
Confidence
93% confidence
Finding

Standalone examples such as “详情” (details), “用户” (user), and “搜索” (search) overlap with ordinary requests unrelated to Twitter/X. The table does not require Twitter/X context or provide exclusions, leaving the intended invocation scope ambiguous.

Content

No source excerpt is available for this finding.

Example invocation phrases are too broad to distinguish Twitter/X requests from unrelated tasks.

Low
Category
Trigger Abuse
Confidence
90% confidence
Finding

The example commands include standalone words such as “用户” (user), “资料” (profile/information), and “搜索” (search), which commonly occur in unrelated requests. Although the introduction identifies Twitter/X as the domain, the invocation examples do not require that context or explain when these generic terms should not activate the skill.

Content

No source excerpt is available for this finding.