ClawHub
Back to skill

Security audit

抖音评论管理助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Douyin comment-management automation tool, but users should treat it as account-authorized browser automation that can store sessions and post replies.

Reasonable to install if you intend to automate your own Douyin creator comments. Run dry-run first, review reply templates carefully, limit max replies, and keep the .playwright/douyin-profile and output files private because they may contain account session data and scraped user comments.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill describes persistent local storage of scraped comment data and a Playwright browser profile, but it does not declare corresponding permissions or clearly surface those capabilities as part of a permission model. That mismatch can mislead users and host systems about the skill's access to local files, increasing the risk of unintended data exposure or unsafe execution in environments that rely on declared permissions.

Vague Triggers

Medium
Confidence
76% confidence
Finding
The trigger set is broad and generic for comment management tasks, so the skill may be invoked in situations where the user did not intend browser automation, scraping, local session persistence, or batch replies. Because this skill acts on a live creator account and can post content, accidental invocation carries meaningful operational and account-safety risk.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill stores sensitive local artifacts, including comment datasets and persistent account session state under .playwright/douyin-profile, but the description and workflow do not prominently warn users of this data retention. If the machine is shared, backed up insecurely, or later compromised, stored session state and scraped user data could be exposed or abused.

Static analysis

No suspicious patterns detected.