ClawHub
Back to skill

Security audit

抖音运营

Security checks for vulnerabilities and agentic risk

Overview

This is a short Douyin operations guidance skill with no code, data access, persistence, or install-time behavior.

This appears safe to install for users who want concise Douyin operations guidance. The main caveat is that it may activate on general Douyin operations requests, so users should verify the advice against current platform rules before relying on it for compliance or advertising decisions.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation description is broad enough to match many ordinary requests related to Douyin/TikTok operations, which can cause the skill to trigger in situations where the user did not explicitly request it. Over-broad activation increases the chance of unintended instruction injection or policy drift by pulling in domain guidance unnecessarily, even though this specific skill content is otherwise fairly benign.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.