ClawHub
Back to skill

Security audit

小红书-社媒运营专家 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Xiaohongshu social-media analytics helper that uses a disclosed Qinghu API, with some credential and local export considerations users should understand.

Before installing, confirm you are comfortable with the skill using your Qinghu API key, making paid Qinghu API calls after your approval, and creating exported result files for larger Xiaohongshu datasets. Do not use it with data you would not want stored in local export files or sent to Qinghu's API.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs the agent to read API credentials from environment variables (QINGHU_TOKEN / QHKIT_TOKEN) without requiring explicit user consent or warning that sensitive secrets may be accessed. In an agent setting, this can cause silent use of preloaded credentials and unintended transmission of secrets to a third-party API, especially when the skill is user-invocable and designed to make outbound HTTP requests.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill mandates automatic export of datasets and instructs using cached local file paths without first notifying the user that files will be created or that data may persist on disk. This creates a privacy and data-handling risk because scraped social/media analytics data may be stored locally longer than expected and could be exposed to other tools, sessions, or operators depending on the runtime.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill is written entirely in Chinese and frames the behavior around Chinese-language operation, but nowhere offers the user a language or locale choice. Under the policy, a fixed language requirement without opt-in can be a natural-language locale violation unless clearly justified and documented as region-specific.

Content

No source excerpt is available for this finding.