Back to skill

Security audit

suansuan-10agents

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language finance analysis prompt skill with no code, network access, persistence, or hidden system changes, though its activation wording is broad.

Install this if you want a Chinese-language finance/business analysis assistant. Be aware it may trigger on broad money-related mentions, and users should avoid sharing sensitive financial details unless they intend the assistant to analyze them.

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
  • 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

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger scope is extremely broad ('只要涉及钱的问题,立即触发本skill'), so the skill can hijack many ordinary conversations that merely mention money, pricing, or costs. This creates routing/instruction-collision risk: users may be forced into this financial persona when they did not request it, reducing relevance and potentially causing inappropriate collection or processing of sensitive financial information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description and opening behavior are written to force Chinese-language interaction without indicating that this is a documented locale-specific skill or giving users a language choice. While not a classic security bug, it can degrade user control and comprehension, which is risky in a finance context where misunderstandings about numbers, obligations, or recommendations can have real consequences.

Content

No source excerpt is available for this finding.