Back to skill

Security audit

Money Maker Hand

Security checks for vulnerabilities and agentic risk

Overview

This prompt-only skill is a coherent Chinese-language money-making research and tracking assistant, with disclosed but privacy-relevant external research and local state persistence.

Install only if you want a Chinese-market focused income-opportunity assistant. Before using it with sensitive business plans or personal income details, decide whether you are comfortable with external platform research and local memory/file retention, and consider asking the agent to confirm before writing income_database.json or storing memory.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill metadata and operational content are presented in Chinese and target Chinese-language platforms, but there is no statement that this locale is optional or intentionally region-specific. SQP-3 applies when a skill appears to force a specific language or locale without user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill directs research across multiple third-party platforms, but does not disclose that network access may occur or what queries/data may be sent externally. This can expose user interests, business ideas, or account-linked browsing activity to external services without transparency, increasing privacy and operational risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly persists state by updating income_database.json and stored memory, but it does not warn the user that local data will be modified or describe what data is retained. Silent persistence can lead to unintended data retention, overwriting existing files, or accumulation of sensitive financial/planning information without informed consent.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The manifest describes an assistant for discovering money-making opportunities, conducting market research, and generating reports. Line L238 states the skill uses sessions_send as a dashboard substitute, which implies pushing updates to external session/UI channels; that capability is not an obvious requirement of market research or report generation itself.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.