Security audit

stock-analysis-five-dimension

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only A-share stock analysis skill is coherent, but it tells the agent to give concrete trading ratings, position sizes, and stop-loss levels to retail users.

Review this skill carefully before installing. It is best treated as a Chinese-language A-share research checklist, not as personalized financial advice; verify all market data independently and avoid relying on its position sizing, buy/sell-style labels, or stop-loss suggestions for real-money decisions without qualified 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

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 (5)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: Although the file ends with a generic disclaimer, the operative instructions tell the agent to output '明确的评估结论、仓位建议和风险提示' and later include '止损设定', which amounts to concrete investment guidance. A weak disclaimer does not offset the fact that the skill operationalizes risky financial behavior without a strong, front-loaded warning, suitability checks, or constraints against personalized advice, creating a real risk of harmful financial decisions by users.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill explicitly activates for broad categories like '个股分析', '选股建议', and '投资决策', which are common user intents and can cause the agent to deliver high-stakes financial guidance in many routine conversations. Because the skill also instructs the agent to provide clear conclusions, position sizing, and trading timing, the broad trigger increases the chance of unqualified or insufficiently contextualized investment advice being surfaced as if actionable.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: This markdown file contains user-facing instructions exclusively in Chinese, and there is no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This markdown file contains end-user instructional content entirely in Chinese, and nowhere indicates that the skill is China-only or otherwise region-specific. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: SQP-3 applies to all file types and includes language or locale policy violations. This markdown file presents all user-facing guidance only in Chinese, with no opt-in, alternative language, or justification for a Chinese-only constraint.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.