Security audit

A股市场情绪量化

Security checks for vulnerabilities and agentic risk

Overview

This is a simple A-share market sentiment guide with no executable code, but its direct position-sizing suggestions should be treated cautiously as financial advice.

Before installing, understand that this skill may produce direct trading posture suggestions based on simplified market indicators. Verify data freshness, apply your own risk controls, and do not rely on it as personalized financial advice or as a basis for concentrated trades.

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 (3)

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The skill gives concrete position recommendations like '轻仓或空仓' and '重仓主线龙头' based on simple heuristics, but it does not warn users about financial risk, uncertainty, or the non-advisory nature of the output. This is especially risky in an A-share short-term trading skill because users may over-trust the model and take leveraged or concentrated positions based on incomplete or stale data.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger phrases are broad everyday trading questions such as '今天市场情绪怎么样' and '能不能加仓', which can cause the skill to activate in general market conversations without clear user intent. In a financial-trading context, unintended invocation is more dangerous because it may inject position-sizing guidance into ordinary discussion and influence risky decisions.

Natural-Language Policy Violations

Low

Confidence: 83% confidence
Finding: The skill content, trigger phrases, and instructions are entirely in Chinese, which implicitly constrains interaction to a specific language/locale. The file does not state that the skill is intentionally region-specific in language terms or offer any user opt-in or alternative language support.

Static analysis

No suspicious patterns detected.