a-stock-stop-loss

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:21 PM UTC
• Version:
  1.0.0

Overview

This is a small text-only A-share stop-loss guidance skill with no evidence of code execution, data access, persistence, or hidden behavior.

Install only if you want educational stop-loss guidance for A-share discussions. Before applying any rule, ask the agent to confirm the context, your risk tolerance, time horizon, and whether you are seeking general education rather than personalized financial advice.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The trigger phrases are very broad generic investing questions, so the skill may activate in many normal portfolio discussions where the user did not specifically request stop-loss optimization. In a financial-risk context, unintended activation can steer users toward rigid trading actions and override more appropriate context-specific guidance, increasing the chance of harmful or unsuitable advice.

VirusTotal

66/66 vendors flagged this skill as clean.