Security audit

A Share Multifactor Model

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent A-share multifactor modeling skill with a local analysis script and no evidence of hidden persistence, credential access, exfiltration, or destructive behavior.

Install this if you want Chinese-language A-share multifactor and Barra-style analysis. Be aware it expects local CSV inputs and may rely on a separate cn-stock-data skill for market data; review data sources and outputs before using results for financial decisions.

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

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

Findings (5)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger description includes very broad phrases such as '多因子', 'multifactor', 'Barra', '因子模型', and '风险模型', which can match many ordinary finance conversations beyond the narrow intended use. This can cause unintended skill invocation, leading the agent to fetch market/financial data or produce specialized quantitative analysis when the user did not explicitly request this skill, increasing the chance of privacy, correctness, or workflow-integrity issues.

Ae4

Medium

Category: analysis-evasion
Confidence: 80% confidence
Finding: Suspicious Unicode normalization or mixed-script content

Natural-Language Policy Violations

Low

Confidence: 97% confidence
Finding: This markdown file presents all instructional content in Chinese, and there is no indication that the skill supports other languages, offers user opt-in for locale, or is explicitly limited to a China-specific audience for organizational reasons. Under the stated policy, forcing a specific language without user choice can be a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. The module docstring presents the tool in Chinese only, and the same pattern continues in user-facing help text, which forces a specific language without any visible opt-in or explanation that the tool is intended only for a Chinese-speaking or region-specific audience.

Natural-Language Policy Violations

Low

Confidence: 94% confidence
Finding: The argparse description and option help text are user-facing natural-language strings, and they are all written only in Chinese. Under SQP-3, this is a policy concern because the skill mandates a specific language for interaction without offering the user a choice or stating a justified locale restriction.

Static analysis

No suspicious patterns detected.