Back to skill

Security audit

Maxhub Tiktok

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it reports platform-scope mismatches and an unlabeled view-count operation; the review is based on partial evidence.

Consider postponing installation until the platform fallbacks and view-count operation are clarified, the installer version is pinned, and the external API destination is verified. The scan is partial: it covered all listed components, but some local references could not be resolved, so it does 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (8)

An unlabeled view-count-increasing operation is embedded in the encryption-tool reference, exceeding the manifest's stated scope of queries and explicitly labeled interaction/protocol tools.

High
Category
Excessive Agency
Confidence
94% confidence
Finding

A second parameter block under TTencrypt_algorithm describes increasing a video's view count, without a separate endpoint heading or a non-read-only warning. Mixing metric manipulation into an encryption-tool reference could cause an agent to mistake a state-changing operation for routine request preparation, undermining platform metrics and exposing accounts to enforcement. The query-focused skill description makes this mismatch more dangerous, although the documentation alone does not establish that the listed encryption endpoint actually performs the mutation.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/api-video.md (reported line 4024)May include surrounding context.

md
> ⚠️ **协议工具**:此接口生成平台请求令牌,用于 API 请求构造。

> 📌 **合法用途**:此接口生成上游平台要求的请求令牌,等同于 OAuth Access Token 生成,是标准 API 认证流程。

**Full path:** /api/v1/tiktok/web/generate_real_msToken

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

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The installation command runs an unpinned npm CLI, allowing the code executed during installation to change without review. A compromised or malicious future release could execute with the installing user's privileges; this is a supply-chain exposure, although the referenced tool is not an MCP server.

Content

No source excerpt is available for this finding.

Example invocation prompts are broad everyday terms without an explicit TikTok-only activation constraint.

Medium
Category
Trigger Abuse
Confidence
96% confidence
Finding

The usage table presents standalone terms such as “搜索” (search), “分析” (analysis), and “加密” (encryption) as example prompts, although these commonly apply outside TikTok. The file does not explicitly require TikTok context 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
93% confidence
Finding

The documented npx command executes clawhub without specifying a reviewed version. If a subsequently resolved release is compromised, installation can execute attacker-controlled code with the user's privileges; the relevant issue is unpinned CLI execution rather than MCP configuration.

Content

No source excerpt is available for this finding.

The example invocation phrases include generic terms without TikTok-specific scope.

Medium
Category
Trigger Abuse
Confidence
94% confidence
Finding

The example commands include everyday terms such as “搜索” (search), “分析” (analyze), and “加密” (encrypt), which overlap with many unrelated tasks. Although the README identifies this as a TikTok skill, these invocation examples contain no TikTok qualifier or explicit exclusion conditions, creating ambiguity about when the skill should activate.

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

# POST example

TikTok query fallbacks route requests to Douyin endpoints outside the skill's declared platform scope (L333–L336).

Medium
Category
Excessive Agency
Confidence
97% confidence
Finding

The fallback mapping directs TikTok operations to Douyin API paths, silently changing platforms rather than merely changing API versions. Autonomous fallback can submit user-supplied identifiers to an unintended platform-specific operation and return unrelated data as TikTok results, creating a scope and data-integrity failure; the hostname remains the same, so this is not evidence of a new external recipient.

Content

No source excerpt is available for this finding.