Back to skill

Security audit

xinjianxue-skill-emotion_qa-cn

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed paid API integration for relationship-advice reports, with sensitive onboarding and data-sharing steps that are visible and purpose-aligned.

Install only if you are comfortable using Xinjianxue's external service, sharing the listed personal details for each report, providing a one-time authorization code from the WeChat mini-program, and letting the assistant store service credentials in a secure local secret store. Review the credit cost and promotional credit guidance before use.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:127
Finding

Mandatory Branded Messaging and External Promotional Funnel

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep