Security audit

CN Stock Analysis Pro

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently generates Chinese A-share stock research reports using public market data, with no evidence of hidden persistence, credential access, destructive behavior, or privilege escalation.

Install only if you want an automatically triggered Chinese A-share research-report workflow. Expect it to query public finance websites with the stock code/name you provide, and treat the generated report as informational rather than investment advice.

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
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (7)

Vague Triggers

High

Confidence: 96% confidence
Finding: The skill’s trigger conditions are extremely broad: any mention of a 6-digit A-share code, stock name, wanting analysis, or asking to 'look at this stock' causes immediate activation. In a general assistant, this can hijack ordinary finance-related conversations, causing unintended tool use, unnecessary data collection, or bypass of more appropriate workflows and user confirmation.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill advertises automatic collection of real-time quotes, financials, capital-flow data, and industry information from third-party sources, but it does not warn users that their query context or requested ticker may be transmitted externally. Lack of disclosure undermines informed consent and can expose sensitive investment interests, watchlists, or proprietary research topics to outside services.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The skill description mandates generation of Chinese A-share strategy reports in Chinese without indicating that language or locale can be adjusted. While not a direct code-execution issue, forcing a language/locale can mislead users, reduce transparency, and increase the chance of user error if the report is consumed by someone expecting another language or market context.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The README states that entering a stock code is sufficient to trigger the skill, but the broader skill metadata also indicates activation on vague phrases like asking to 'look at this stock' or generate a report. Overly broad invocation criteria can cause unintended activation and external data collection or report generation without clear user intent, which is risky for a skill that reaches out to multiple finance data sources.

Natural-Language Policy Violations

Medium

Confidence: 98% confidence
Finding: This markdown file presents all operational instructions in a single mandated language and does not indicate that users may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless clearly justified as region-specific.

Natural-Language Policy Violations

Medium

Confidence: 97% confidence
Finding: The document title and all report instructions are written in Chinese, indicating the skill is intended to produce output in a specific language by default. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified, which is not stated here.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The HTML root element sets lang="zh-CN", which enforces a specific locale for generated reports. The file does not provide a user-selectable locale option or explain that the report is for a China-specific compliance or audience context, so this conflicts with the language/locale policy.

Static analysis

No suspicious patterns detected.