Security audit

A Stock Analysis Lite

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese A-share research-report generator that uses public market data and local HTML output, with no evidence of hidden execution, credential use, persistence, or exfiltration.

Install this if you want Chinese-language A-share research reports from public data. Be aware it may activate on simple stock-code or stock-name mentions, and its output is financial analysis, not investment advice; users should verify market data independently before acting.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (7)

Vague Triggers

High

Confidence: 96% confidence
Finding: The skill’s activation criteria are extremely broad: any mention of a 6-digit A-share code, stock name, or generic request to 'analyze this stock' causes automatic invocation. This can hijack ordinary market discussion, override user intent, and trigger unnecessary data collection or report generation in contexts where the user did not explicitly ask to use the skill.

Natural-Language Policy Violations

Medium

Confidence: 89% confidence
Finding: The skill is described as generating Chinese A-share strategy reports, which fixes the output language and market locale without indicating user choice. This can cause the agent to ignore user language preferences or broader context, reducing reliability and potentially producing unsuitable output for users expecting another language or market scope.

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The README states that installing the skill and inputting a stock code is sufficient to trigger analysis, which is a broad activation condition for an agent skill handling financial analysis. Overly permissive triggers can cause the skill to activate when the user did not explicitly request this workflow, leading to unintended data fetching, report generation, or financial-analysis responses that override user intent.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The skill mandates Chinese-language output without checking the user’s language preference. While not a direct code-execution risk, it can cause unsafe or misleading UX by overriding user expectations, reducing comprehension, and making financial analysis less accessible to users who requested another language.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: This markdown file consists entirely of prompts and instructions written to produce analysis in Chinese, including fixed Chinese output labels and phrasing requirements. The file does not offer a language/locale option or explain that the skill is intended only for a Chinese-language or region-specific workflow, which makes it a natural-language locale policy concern.

Natural-Language Policy Violations

Medium

Confidence: 97% confidence
Finding: The document title and all operational instructions are written exclusively in Chinese, which effectively imposes a single language on users or downstream agents. There is no indication that language selection is optional, user-configurable, or required for a documented region-specific compliance reason.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The HTML template hard-codes `lang="zh-CN"`, and the surrounding document content is written entirely in Chinese, which imposes a specific language/locale on users. The file does not provide an opt-in, alternative locale, or justification that this template is strictly for a China-specific compliance or regional workflow.

Static analysis

No suspicious patterns detected.