Security audit

Overseas Investment Compliance

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese cross-border investment compliance guide with no executable code, persistence, credential access, or hidden system behavior.

Before installing, confirm that users need Chinese-language PRC/cross-border investment compliance triage and that they understand this is not legal advice. For real transactions, verify current rules with official sources and qualified counsel, especially because the skill gives specific approval paths, timelines, costs, and risk ratings.

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 (6)

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The skill is written to operate in Chinese throughout and does not offer user language choice or document a justified locale restriction. This can create safety and accuracy issues in a legal/compliance context because users who are not fluent in Chinese may misunderstand approval paths, risk ratings, or prohibitions, leading to incorrect reliance on the guidance.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger table includes broad, common phrases such as asking whether something is compliant or how to move money overseas, which can cause the skill to activate outside its intended scope. In a regulated compliance domain, accidental activation is risky because the assistant may steer users into specialized legal/compliance guidance without first confirming that this skill is the right fit, increasing the chance of misleading or overconfident advice.

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: This markdown file presents all user-facing policy content exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into this language. Under the language/locale policy rule, forcing a specific language without user choice can be a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 91% confidence
Finding: This markdown file contains user-facing instructions exclusively in Chinese, and there is no indication that users may choose another language or that the content is intentionally limited to a Chinese-speaking or China-specific audience. The policy category requires flagging language or locale constraints when a specific language is forced without user opt-in.

Natural-Language Policy Violations

Low

Confidence: 91% confidence
Finding: The entire markdown file is written exclusively in Chinese, with no indication that language selection is optional or that the skill is region- or locale-specific. Under the language/locale policy rule, forcing a specific language without user opt-in can be a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 94% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all instructions and content exclusively in Chinese, with no user opt-in, language alternative, or justification that the skill is intended only for a Chinese-language audience.

Static analysis

No suspicious patterns detected.