ClawHub
Back to skill

Security audit

Ozon-竞店截流专家 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Ozon competitor-shop research workflow that uses a Qinghu API token and external data calls with user confirmation before tool use.

Before installing, understand that this skill is meant to call Qinghu's API for Ozon competitor research and may use your Qinghu token from an environment variable or by asking you. Review the tool list and cost prompt before approving calls, and expect exported local files when larger result sets are returned.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill description explicitly says it 'must trigger' for broad competitor-analysis intents such as analyzing a shop, monitoring competitor products, or replicating selection logic. Because these intents are common and overlap with ordinary marketplace research requests, the skill can be invoked when the user did not intend a costly or credential-requiring workflow, increasing the chance of unnecessary data access, external calls, and spend authorization prompts.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The listed trigger phrases are short, generic, and likely to appear in routine conversation, such as 'analyze this Ozon shop' or 'what is the competitor selling.' In this skill, accidental triggering is more dangerous because invocation may lead to external API usage, token handling, and paid tool calls under a workflow that is framed as mandatory for those phrases.

Static analysis

No suspicious patterns detected.