ClawHub
Back to skill

Security audit

douyin-hot

Security checks for vulnerabilities and agentic risk

Overview

This skill narrowly fetches Douyin hot-search data and saves a local JSON copy, with no evidence of hidden commands, credential access, or persistence beyond the disclosed output file.

Before installing, be aware that running the skill makes a network request to Douyin using browser-like headers and writes the latest results to workspace/scripts/douyin-hot-clean.json, replacing any prior file at that path. It does not appear to read credentials, modify agent settings, install dependencies, or persist background behavior.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The request hard-codes Accept-Language: zh-CN,zh;q=0.9,en;q=0.8, which imposes a specific locale preference in the skill's behavior. This is a natural-language locale policy concern because the file provides no user opt-in or documented reason for forcing Chinese language preferences.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill states that scraped results are saved to a workspace file, but it does not clearly warn the user that running the skill will persist data or modify the workspace. This can lead to unexpected data retention, overwrite of prior output, or leakage of scraped content into shared/project state, especially in multi-step agent workflows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.