ClawHub
Back to skill

Security audit

Tiktok Script

Security checks for vulnerabilities and agentic risk

Overview

This skill is a content-writing helper for TikTok scripts, and its file reads, style rules, AI-video notes, and scheduling handoffs are disclosed and aligned with that purpose.

Installers should understand that this skill may steer ambiguous 'storytime' requests toward TikTok scripting and will use any available brand profile or voice file to shape output. Review generated captions, AI-video prompts, and any scheduling handoff before publishing public content.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list includes broad, generic phrases such as "storytime" and "make a TikTok," which can cause this skill to activate for loosely related requests without clear TikTok-specific intent. Over-broad routing is dangerous because it can mis-handle user requests, bypass more appropriate skills, and create unintended downstream actions such as invoking other tools or workflows based on an imprecise match.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file instructs that output must use a predefined blunt indie-founder voice and specifically says to use the loaded voice.md. This is a natural-language style/locale constraint imposed by default, with no indication that the user can choose another language or voice.

Content

No source excerpt is available for this finding.