Security audit

赵克常老师SKILL

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese investment-analysis framework with disclosed financial-risk caveats and no code, persistence, or data-access behavior, though users should treat its trading guidance cautiously.

Install only if you want a Chinese-language investment-analysis checklist and workflow. Treat its buy, sell, stop-loss, and position-sizing outputs as educational prompts, verify market data independently, and do not rely on it as personalized financial advice or automated trading authority.

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 (6)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description is very broad and can trigger on many loosely related investment or strategy questions, increasing the chance the agent invokes this skill when the user did not explicitly request investment analysis. Over-broad activation can cause inappropriate automation, irrelevant financial guidance, or accidental bypass of more suitable domain-specific workflows, which is especially sensitive in a financial decision-support context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The skill content is entirely in Chinese and does not document language selection behavior, fallback rules, or whether it should adapt to the user's language. This can lead to unintended language forcing, misunderstanding of financial guidance, and poor user comprehension in a high-stakes context where clarity materially affects decisions.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The document provides concrete investment decision, trading, stop-loss, and position-management guidance without any disclaimer that it is educational information rather than personalized financial advice, and without warning about market risk or loss of principal. In the context of an investment-analysis skill, users may reasonably rely on this workflow to make real trades, increasing the chance of financial harm or inappropriate reliance on the agent.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The checklist provides explicit buy-side guidance and scoring thresholds such as 'strongly recommend buy' and 'recommend buy' without any disclaimer about financial risk, suitability, or that the content is educational rather than personalized investment advice. In an investment-analysis skill, this increases the chance that users will treat heuristic checklist outputs as actionable advice and suffer financial loss from overreliance on simplified criteria.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The document instructs users to execute stop-loss and sell decisions 'unconditionally' and 'immediately' without warning about slippage, gaps, volatility, liquidity constraints, or the possibility of locking in irreversible losses during abnormal market conditions. In a trading-oriented skill, such absolute language can encourage unsafe execution behavior and cause users to act mechanically in situations where context-sensitive risk management is necessary.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The file's natural-language content appears to require Chinese, which can constitute a language/locale policy issue when no user opt-in or justification is provided. There is no accompanying note that the skill is intended specifically for Chinese-speaking users or that alternate languages are unavailable by design.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.