Back to skill

Security audit

宝总霸盘Skill — 全市场智能操盘系统

Security checks for vulnerabilities and agentic risk

Overview

This is a stock-analysis guidance skill with broad financial triggers, but it does not install code, execute trades, persist processes, or hide data access.

Install only if you want a Chinese stock-analysis assistant. Be aware that it may activate on broad finance-related phrases and may produce buy/sell-style analysis templates; verify market data independently and do not treat its output as professional investment advice.

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
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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill declares extremely broad activation terms covering many common investing topics and keywords, which increases the chance it will trigger during ordinary finance conversations even when the user did not intend to invoke this skill. Over-broad activation can cause unintended routing, overshadow more appropriate skills, and expose users to unsolicited trading-oriented guidance in sensitive financial contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
76% confidence
Finding

The skill's natural-language description, trigger phrases, output templates, and examples are all written as Chinese-only interaction patterns, with no indication that users may choose another language. Under the stated policy, a language constraint should be optional or explicitly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger phrases around the market-analysis section include short, ambiguous prompts such as requests for analysis that many users could say conversationally without meaning to invoke this particular skill. This creates accidental activation risk and can result in the model providing specialized investment workflow outputs where a general response or clarification would have been safer.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The daily review trigger includes generic phrases like '今天怎么样' or '收盘了', which are common conversational expressions and may match contexts unrelated to portfolio review. While lower severity than the top-level activation block, it still risks unintentional skill execution and confusing or inappropriate finance-specific responses.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The risk-check trigger relies on broad prompts like '账户怎么样' and '看看风险', which could refer to many non-trading contexts. This can misroute user intent into an investment risk workflow and generate unsuitable financial recommendations or assumptions about holdings.

Content

No source excerpt is available for this finding.