Security audit

A Share Risk Alert

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-market stock risk analysis skill with no executable code, persistence, credential access, or hidden high-impact behavior.

Before installing, users should understand that this skill is for A-share stock-risk screening and may use web search plus market-data tools. Treat its output as research support, not investment advice, and be aware that broad Chinese phrases like 'is it safe' may trigger it outside stock contexts unless clarified.

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 (3)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger phrases are broad enough to match ordinary conversational queries such as '有没有风险' or 'XX安全吗', which can cause the skill to activate outside its intended stock-risk context. This creates routing ambiguity and may lead to unintended interception of user requests, incorrect financial analysis responses, or suppression of more appropriate skills.

Natural-Language Policy Violations

Low

Confidence: 73% confidence
Finding: All user-facing instructions and invocation examples are written only in Chinese, and the trigger model assumes Chinese phrasing without indicating whether other languages are supported or whether Chinese is required by design. Under the policy, language constraints should be optional, user-selectable, or explicitly justified as region-specific.

Natural-Language Policy Violations

Low

Confidence: 93% confidence
Finding: This markdown file contains natural-language guidance exclusively in Chinese and does not indicate that the user can choose another language. Under the policy rule for language or locale constraints, forcing a single language without user opt-in can be a policy violation unless it is explicitly documented as region-specific and justified.

Static analysis

No suspicious patterns detected.