Back to skill

Security audit

十维

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language stock analysis checklist with no executable code, persistence, credential handling, or hidden system behavior, though users should treat its investment conclusions as informational only.

Install only if you want a Chinese-language framework for stock fundamental analysis. Verify all financial data independently and treat outputs such as '可考虑配置' or '直接排除' as informational analysis, not personalized investment advice.

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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill produces recommendation-like conclusions such as 重点关注, 可考虑配置, and 直接排除, but does not clearly disclose that outputs are informational rather than financial advice. In a financial decision-making context, this increases the risk that users over-rely on the skill's judgments and make consequential investment decisions without appropriate caveats or suitability checks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill hard-requires invocation whenever the very common term "十维" appears, without checking whether the user actually wants stock analysis. This can cause inappropriate tool routing, context hijacking, and unintended activation in unrelated conversations, increasing the chance of irrelevant or risky financial-analysis output.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The alternate triggers include broad phrases like 价值研判, 财务分析标准流程, and 深度财务分析, which are generic enough to match many benign or unrelated finance discussions. Overbroad activation boundaries can lead to unsolicited investment-style analysis, misrouting away from safer general responses, and accidental use in contexts where the user did not request this framework.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The entire template, headings, instructions, and example content are written in Chinese with no indication that users may choose another language or that the skill is intended only for a Chinese-language or region-specific context. This creates a natural-language locale policy concern because it effectively mandates one language without opt-in or justification.

Content

No source excerpt is available for this finding.