ClawHub
Back to skill

Security audit

养老规划助手

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown retirement-planning guidance skill with no code, persistence, credential use, or hidden data movement.

Before installing, consider that the skill gives financial and policy-oriented retirement guidance and may ask for personal financial details. Treat its calculations and policy statements as general planning help, not professional financial, legal, medical, or tax advice, and avoid sharing more personal information than needed.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains broad everyday phrases such as “养老金”, “退休规划”, “如何养老”, and the English term “retirement planning”, which can match normal conversation outside a narrow skill-invocation context. Overly broad triggers can cause unintended activation, making the agent respond in contexts where users did not explicitly request this skill and increasing the risk of inappropriate financial or planning guidance being injected into unrelated chats.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.