Back to skill

Security audit

Maxhub Kuaishou

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because its instructions reportedly allow Kuaishou requests to fall back to Douyin APIs, and the scan also flags an unpinned installer and data sent to an external service.

The verdict is suspicious, so consider the reported risks before installing. Review the cross-platform fallback and external data sharing, and use a reviewed, exact installer version if you proceed. The scan covered all seven listed components but was marked partial because several references could not be resolved, so the 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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (7)

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

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The installation command runs an unpinned npm CLI, so the code executed can change between installations. A compromised future release could execute with the installing user's privileges; this is a supply-chain exposure, although the referenced tool is an installer rather than an MCP server.

Content

No source excerpt is available for this finding.

Usage prompts are generic words that do not distinguish Kuaishou requests from unrelated tasks.

Medium
Category
Trigger Abuse
Confidence
95% confidence
Finding

The example prompts include 搜索 (search), 用户 (user), 资料 (information), and 分享 (share), which occur in many unrelated requests. Although the README identifies the skill as a Kuaishou assistant, it does not constrain these prompts to explicit Kuaishou requests or provide exclusions, leaving the invocation scope ambiguous.

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 installation command executes clawhub without an exact version, allowing newly published package code to run during installation. A compromised release could access the installing user's files and credentials; the risk is unpinned installer execution, not an identified MCP server.

Content

No source excerpt is available for this finding.

The example invocation phrases are generic words without an explicit Kuaishou-specific activation constraint.

Medium
Category
Trigger Abuse
Confidence
94% confidence
Finding

The example commands include “用户” (user), “搜索” (search), and “分享” (share), which commonly appear in unrelated requests. Although the README describes a Kuaishou assistant, these invocation examples do not require Kuaishou context or provide exclusions, leaving the activation boundary ambiguous.

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

# POST example

The query workflow lacks a privacy warning about sending user-supplied search terms and target identifiers to MaxHub.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow instructs the agent to search for users and retrieve their profiles and videos, executing planned queries autonomously through the third-party MaxHub API. Although the file identifies the provider and includes a data-accuracy disclaimer, it does not warn that user-supplied query terms and target identifiers will be transmitted to that provider.

Content

No source excerpt is available for this finding.

The fallback table routes Kuaishou queries to Douyin APIs, outside the skill's declared platform scope.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The fallback mapping specifies Douyin endpoints despite the skill being scoped to Kuaishou, and the workflow authorizes autonomous fallback calls. If a mapping is reached, it can send identifiers to an unintended platform-specific API and return unrelated data as part of a Kuaishou analysis; the listed source endpoint names may limit when this occurs.

Content

No source excerpt is available for this finding.