ClawHub
Back to skill

Security audit

Visual Benchmarker

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed workflow skill for finding Douyin visual reference videos, with a normal privacy caution around search keywords derived from user materials.

Before installing, understand that this skill is an instruction-only workflow and relies on a separate Douyin/TikHub search integration. Use it with materials you are comfortable turning into external search terms, and redact confidential client, product, personal, or unreleased strategy details before running searches.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill tells the AI to ingest user-provided materials and derive search queries that are then sent to an external video-search dependency, but it does not require any user notice, consent, or redaction step before external transmission. If the uploaded materials contain confidential business plans, product details, or personal data, sensitive information could be disclosed to the downstream tool through generated keywords or follow-up queries.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The skill's natural-language interface and operating instructions are entirely in Chinese and present the workflow in that language by default. There is no indication that users may choose another language, nor a documented reason that the skill must be Chinese-only.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.