ClawHub
Back to skill

Security audit

tiktok-video-search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed TikTok search integration that uses Gecho's MCP workflow and logged-in browser session, with expected local result saving.

Install only if you are comfortable connecting Gecho to a logged-in TikTok browser session and saving TikTok search metadata locally. Use an account and save directory appropriate for the data being collected, and review the external Gecho MCP package and Chrome extension before use if your environment has stricter privacy requirements.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 330)May include surrounding context.

md
Join the [WeCom group](https://github.com/gecho-ai/gecho-bridge/blob/main/qywx.jpg) for community support, or scan the [1:1 support QR code](https://github.com/gecho-ai/gecho-bridge/blob/main/wx.jpg) for personal help.

## Output guidelines

For successful search:

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill requires a live logged-in TikTok browser session and a Gecho extension connected to that session, but the description does not prominently disclose this privacy-sensitive dependency. Users may not realize the tool is operating against authenticated session data, which increases the risk of over-collection, unexpected access to account-visible content, and consent/privacy issues.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly says it may save the full raw TikTok result set to a local JSON file, but the top-level description does not warn users about local persistence of potentially sensitive browsing-derived data. This can cause users to invoke the skill without understanding that creator metadata, links, engagement data, and keyword searches may be written to disk where other local users, backup systems, or tools could access it.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.