Security audit

量化交易知识

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only quant trading skill with no code or persistence, but it directs agents to provide actionable stock buy/sell guidance without meaningful risk or suitability guardrails.

Review this skill carefully before installing. It is not technically invasive, but it is designed to produce actionable trading guidance. Users should treat outputs as educational analysis only, verify market data independently, and avoid relying on it for personalized investment decisions unless appropriate financial-advice safeguards are added.

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 (7)

Missing User Warnings

High

Confidence: 95% confidence
Finding: The skill explicitly lists giving buy/sell recommendations and stock-picking advice, yet it provides no user-facing warning that outputs are educational, uncertain, and not financial advice. In this context, the omission is dangerous because users may treat the agent's output as authoritative trading guidance and make risky financial decisions without understanding limitations.

Missing User Warnings

High

Confidence: 97% confidence
Finding: The template provides concrete trading parameters such as buy range, stop-loss, target price, and position sizing, but includes no cautionary language, assumptions, or uncertainty disclosures. This makes the skill especially dangerous because it operationalizes actionable trades in a form users can immediately follow, increasing the risk of financial harm from inaccurate, stale, or unsuitable advice.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The skill description claims broad use for quant trading questions, stock analysis, and strategy suggestions without clear activation boundaries or safety constraints. This can cause the agent to invoke the skill in situations involving personalized or high-stakes financial guidance, increasing the chance of unsafe or inappropriate investment recommendations.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The purpose statement says the skill is for stock analysis and strategy advice but does not define when it should or should not activate. In an agent setting, that ambiguity can over-trigger the skill for requests that require regulated financial advice safeguards, suitability checks, or stronger disclaimers.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The file gives concrete buy/sell strategy logic and trading guidance without any warning that these strategies can cause financial loss, may not suit a user's risk tolerance, and are not guaranteed to perform. In a quant-trading skill, this increases the chance that users interpret the content as actionable advice and apply it without understanding material risk.

Natural-Language Policy Violations

Low

Confidence: 78% confidence
Finding: This markdown file presents all instructional content in Chinese and does not indicate that the language choice is optional or tied to a documented region-specific requirement. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy concern.

Natural-Language Policy Violations

Low

Confidence: 83% confidence
Finding: The entire skill content is presented only in Chinese, with no indication that language selection is optional or that the document is intentionally limited to a Chinese-speaking or region-specific audience. Under SQP-3, forcing a specific language without user opt-in can constitute a natural-language policy violation.

Static analysis

No suspicious patterns detected.