Security audit

A股龙头股识别

Security checks for vulnerabilities and agentic risk

Overview

The skill contains no code or data access, but it gives aggressive short-term stock-trading guidance without risk warnings or suitability checks.

Review carefully before installing. This skill should be treated as speculative financial-analysis guidance, not personalized investment advice; users should expect volatility and potential losses and should verify any output independently before trading.

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)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill gives direct, actionable trading instructions like locking onto a leader stock and following immediately, but provides no warning about financial risk, suitability, or the speculative nature of short-term trading. This is especially risky because the skill is explicitly designed for fast A-share stock selection, increasing the chance users act on the guidance as investment advice without understanding loss potential.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger phrases are broad and ambiguous, so the skill may activate for general market discussion rather than explicit requests for this specific stock-selection workflow. In a financial-trading context, unintended activation is more dangerous because it can inject narrow, high-risk trading guidance into conversations where the user did not clearly request speculative advice.

Natural-Language Policy Violations

Low

Confidence: 80% confidence
Finding: All user-facing description and trigger phrases are written in Chinese, with no indication that this is a deliberate region-specific limitation or that users may choose another language. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation.

Static analysis

No suspicious patterns detected.