Security audit

Asset Allocation

Security checks for vulnerabilities and agentic risk

Overview

The skill is not malware, but it gives personalized investment and purchase guidance with weak locale and suitability boundaries.

Review this carefully before installing if you may use it outside mainland China or for regulated/personalized financial advice. Treat its allocations, product names, product codes, rates, and purchase steps as educational prompts only, and verify suitability, licensing, current product data, and local rules with a qualified professional 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

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 (8)

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The skill description says to use it whenever users ask about investing, wealth management, fund/ETF selection, retirement planning, or asset allocation, which is broad enough to trigger on many finance-related conversations without first establishing jurisdiction, suitability, or whether regulated advice is appropriate. In this context, overbroad activation increases the chance the agent will deliver personalized investment guidance in situations where only general education should be provided.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The quick-start condition 'When user asks about investment/wealth topics' is ambiguous and lacks scope boundaries, causing the skill to activate before determining whether the request is generic education, individualized financial advice, or outside permitted scope. In an investment advisory skill, that ambiguity is more dangerous because the workflow immediately proceeds to profile collection, allocation, and execution planning.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The execution phase hardcodes Chinese platforms and product-purchase flows without asking the user’s locale or confirming those platforms are relevant, effectively steering users into a specific regional context. In a financial skill, this can mislead users, create unsuitable or inapplicable recommendations, and increase regulatory/compliance risk when platform availability, product rules, and investor protections differ by jurisdiction.

Natural-Language Policy Violations

Medium

Confidence: 89% confidence
Finding: The entire document is written in Chinese and is specifically framed around China-market macro analysis, A-shares, RMB, and Chinese data sources without any indication that language or locale is optional. The policy only allows such locale constraints when they are explicitly offered as a choice or clearly documented and justified as region-specific; this file does not state that limitation explicitly.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: This markdown file contains user-facing guidance exclusively in Chinese, and nowhere indicates that the user may choose another language or that the content is intentionally limited to a China-specific audience. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy concern.

Natural-Language Policy Violations

Medium

Confidence: 84% confidence
Finding: The overview states that the guide provides purchase instructions across platforms in China, and the document consistently assumes a China-specific locale and platform ecosystem throughout. Under the policy rule, locale-specific guidance should either offer user choice/opt-in or clearly document and justify the regional constraint; this file does not explicitly do so.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: This markdown file presents all instructions and guidance only in Chinese, and there is no indication that the user can choose another language or that the skill is intentionally restricted to a Chinese-speaking or China-specific audience. Under the language/locale policy, forcing a specific language without opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 84% confidence
Finding: The entire markdown file is written exclusively in Chinese and does not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the stated policy, a fixed language without opt-in or justification can be a natural-language policy violation.

Static analysis

No suspicious patterns detected.