ClawHub
Back to skill

Security audit

qiye-risk-platform

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language guide for building a PatSnap/Eureka-based financial risk demo platform, with no hidden execution, persistence, or destructive behavior found.

Before installing, confirm you are authorized to send enterprise names or credit codes to PatSnap/Eureka MCP services, especially for confidential client or portfolio lists. Treat generated reports as risk-analysis support rather than final credit decisions.

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
94% confidence
Finding

The skill explicitly instructs users to perform 'real queries' against PatSnap/Eureka interfaces using enterprise names and identifiers, but it does not clearly disclose at the point of data entry that these values will be transmitted to external services. In a financial risk-management context, enterprise identifiers, lookup targets, and query activity may be sensitive business information, so silent transmission can create privacy, confidentiality, and compliance risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
75% confidence
Finding

The skill's natural-language instructions, headings, prompts, and expected outputs are all presented in Chinese, with no indication that users may select another language. Under the policy, forcing a specific language without opt-in can be a locale/language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.