Back to skill

Security audit

Maxhub Xiaohongshu

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because its fallback instructions may send requests to a different platform than the stated Xiaohongshu scope; the scan is incomplete, so this is a review warning rather than a conclusion of malicious intent.

Consider the platform mismatch and unpinned installer before installing. The scan examined 8 of 9 components fully and one partially, so the evidence is incomplete; the suspicious verdict signals issues to review and does not establish malicious intent.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 184)May include surrounding context.

md
ote Data** | 笔记, 详情, 评论, 子评论, note, detail, comment, sub_comment, info, feed | `references/api-note.md` | extract_share_info, search_notes, get_topic_notes, get

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

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The installation command runs an unversioned npm CLI through npx, allowing the code executed during installation to change without a documentation change. A compromised or malicious upstream release could execute with the installer's privileges; this is a supply-chain exposure, although the snippet references an installer rather than an MCP server.

Content

No source excerpt is available for this finding.

Example invocation prompts use generic words without Xiaohongshu-specific scope.

Medium
Category
Trigger Abuse
Confidence
95% confidence
Finding

The example prompts include generic terms such as “详情” (details), “用户” (user), and “搜” (search), which commonly occur in requests unrelated to Xiaohongshu. Although the README identifies the platform, these invocation examples do not require that context or provide exclusions, creating ambiguity about when the skill should activate.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The documented npx command does not pin the clawhub package version, so installation can execute a newly published release rather than a fixed reviewed artifact. If the upstream package or publishing account is compromised, that release could execute arbitrary code with the installer's privileges; the MCP-server label is inaccurate, but the supply-chain risk remains.

Content

No source excerpt is available for this finding.

Example invocation phrases are too broad to reliably identify Xiaohongshu requests.

Medium
Category
Trigger Abuse
Confidence
95% confidence
Finding

The example commands include generic terms such as “详情” (details), “用户” (user), and “搜索,搜” (search), which commonly occur in unrelated requests. Although the introduction identifies Xiaohongshu 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.

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

# POST example

The fallback instructions route requests to Douyin APIs despite the manifest declaring a Xiaohongshu-only data assistant.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The fallback table directs the agent to Douyin endpoints despite the skill's Xiaohongshu scope and permits automatic fallback execution. If applied, it could send task parameters to an unintended API product, incur unwanted charges, or return misleading cross-platform results; however, the listed failing endpoints are also Douyin-specific, so ordinary Xiaohongshu requests may never trigger these mappings.

Content

No source excerpt is available for this finding.