Back to skill

Security audit

A股十书全景分析法

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only A-share stock analysis skill with disclosed financial-analysis behavior and no hidden execution, persistence, or credential access.

Install only if you want Chinese-language A-share stock analysis. Treat price ranges, position percentages, and buy/watch/avoid ratings as informational, verify market data independently, and do not rely on the skill as professional financial 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad enough that ordinary stock-related user messages may auto-activate this skill without clear user intent to invoke it. In a finance context, unintended activation is risky because the skill can produce concrete trading advice and fetch external market data, increasing the chance of unrequested or context-inappropriate financial guidance.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises real-time market analysis, backtesting, and specific trading actions, but the warning only says the content is not investment advice and does not disclose that external data may be delayed, incomplete, stale, or unavailable. In this context, users may over-trust time-sensitive recommendations that depend on third-party APIs and web search results, creating a meaningful risk of harmful financial decisions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The quick-start instruction states that sending a stock name and code is sufficient to trigger analysis, but it does not define boundaries, exclusions, or confirmation requirements. That ambiguity can cause accidental invocation during general financial conversation, leading the system to generate unsolicited analysis or action-oriented recommendations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The template headings and required output structure are entirely specified in Chinese, which indicates a fixed language expectation. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified or optional.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.