ClawHub
Back to skill

Security audit

Tiktok Bulk Publisher

Security checks for vulnerabilities and agentic risk

Overview

This skill is for TikTok bulk publishing and is not malicious, but it asks for account API credentials and describes mass posting without enough scoping or safety guidance.

Install only if you are comfortable giving an agent TikTok API publishing credentials. Use a test or low-risk account first, store and rotate the client secret carefully, review any config and script implementation before running it, and confirm how posts are previewed, approved, scheduled, and limited before allowing bulk publication.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This skill requests TikTok OAuth client credentials and performs bulk publishing, but the documentation does not warn users about account-level consequences, token/secret handling, rate limits, or the risks of automating publication. In a publishing automation context, missing safety guidance increases the chance of credential mishandling, unintended mass posting, or misuse against a user's social-media account.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The primary natural-language description is written in Chinese, and the document does not indicate that the skill is region-specific or provide an explicit user language choice. Under the language/locale policy, forcing a specific language without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

SKILL.md 在功能列表中声明了自动剪辑、音乐推荐、标签优化和时段分析等能力，但同一文件的 manifest 描述仅聚焦于批量上传发布、OAuth 授权和标题/隐私/互动设置。就当前提供的技能文件而言，这些附加能力超出了已声明的核心行为，形成描述范围不一致。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.