Security audit

AI-Technical-Analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language stock technical-analysis tool that fetches market data and prints indicator reports, with no evidence of hidden persistence, credential access, or unrelated system behavior.

Install this only if you want a Chinese-language A-share technical-analysis helper. Treat its buy/sell and breakout language as informational analysis, not personalized investment advice, and confirm before using it for broad market-opportunity scans.

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)

Ae1

High

Category: analysis-evasion
Content: 2. 调用 `scripts/quant_analyzer.py` 执行分析：
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: 2. 调用 `scripts/quant_analyzer.py` 执行分析：
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: 2. 调用 `scripts/quant_analyzer.py` 执行分析：
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger for stock or index technical analysis is broad enough that many ordinary finance-related questions could invoke the skill unintentionally. In an investment context, accidental invocation can cause the agent to fetch market data, generate trading-oriented analysis, and present quasi-advisory outputs where the user did not clearly request this workflow.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The opportunity-detection examples like finding recent breakout signals or analyzing fund flows are ambiguous and may over-trigger on broad market-opportunity questions. Because this skill is designed to surface trading signals, an overly permissive trigger can amplify risk by steering users toward speculative outputs without clear consent or suitability checks.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The module description and all user-facing report strings are written in Chinese, and the skill does not provide any option for users to select another language or locale. This creates a natural-language locale policy issue because the skill effectively enforces a specific language by default without opt-in or justification.

Static analysis

No suspicious patterns detected.