Security audit

A股观察循环

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, instruction-only A-share market checklist helper with no executable code, credential access, persistence, or hidden data movement.

Before installing, understand that this skill is meant to structure stock-market review checklists, not execute trades. Only share holdings or portfolio details you are comfortable providing, verify real-time market data independently, and treat its pass/fail actions as decision-support rather than financial advice.

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 (2)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The invocation cues are generic user phrases such as '把观察项落下来' and '用户要每日复核框架', which can match many ordinary finance/planning requests and cause the skill to trigger when the user did not explicitly ask for this workflow. Over-broad activation can hijack routing, override more suitable skills, and steer responses into a rigid checklist format that may not fit the user's intent or available data.

Natural-Language Policy Violations

Medium

Confidence: 81% confidence
Finding: The skill metadata description is written only in Chinese and the finding indicates language forcing without user opt-in, which can bias selection and output behavior toward Chinese even when the user has not requested that language. This is primarily a safety and usability issue: it can reduce transparency, confuse users, and interfere with proper consent or correct routing in multilingual environments.

Static analysis

No suspicious patterns detected.