Back to skill

Security audit

A Stock Investment Analyst

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed A-share stock analysis skill with financial-advice risk, but no hidden execution, persistence, credential access, or unrelated data handling was found.

Before installing, understand that this skill can generate concrete stock and portfolio suggestions from information you provide. Do not share account credentials or unnecessary sensitive financial details, verify all market data and dates independently, and treat any buy/sell language as general analysis rather than licensed financial 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
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 8)May include surrounding context.

md
---
AIGC:
    ContentProducer: Minimax Agent AI
    ContentPropagator: Minimax Agent AI
    Label: AIGC
    ProduceID: 8352d094c22f8c0479267a28249e4d2d
    PropagateID: 8352d094c22f8c0479267a28249e4d2d
    ReservedCode1: 3045022100af89ab99381cbdcfd4bc8701f3571db6ed9b0f48d664c407e3c7842a9c60e85e02201b5e3d110ee2b36d333180d9269e95ce0f175074439eb6cd156034f1177c7a26
    ReservedCode2: 3045022100af7ec2f5c09ed9f5d3af4daeaa92ad97c2a47d5d048503feb447580e72f2663802206bbcf04237f875c09ae5b3a65100dab5205626cec4240daaf3d2eb352142b576
description: A股投资分析专家技能。当用户要求分析A股、投资诊断、股票诊断、个股分析、行业分析、板块研究、组合优化、风险预警、新闻解读、资金流向分析、技术面分析、基本面分析时使用。支持股票代码/名称查询、行

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The top-level description activates on a very broad set of common finance-related requests, which can cause this skill to be selected when the user did not clearly request stock-investment analysis. In an agent environment, overly broad routing increases the chance of mis-invocation, irrelevant financial guidance, and accidental handling of sensitive portfolio information under the wrong skill context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The mode triggers are phrased as generic user behaviors like entering a stock code or asking for analysis, without precise gating rules. That ambiguity can cause the orchestrator to route ordinary conversation into an authoritative investment-analysis workflow, increasing the risk of unintended financial advice and over-collection of user financial context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The phrase '请优化我的持仓' is a natural, high-frequency user utterance and the associated trigger accepts highly sensitive portfolio details with little scoping. In practice this can lead to automatic engagement of the skill on ambiguous requests and unnecessary exposure or processing of holdings, risk preferences, and investment goals.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file includes explicit investment action labels such as strong buy, hold, reduce, and avoid without any accompanying risk disclosure, suitability caveat, or statement that outputs are informational rather than personalized financial advice. In an A-share investment analysis skill, this materially increases the chance that users treat generated scores as actionable recommendations, which can lead to financial harm, compliance issues, and overreliance on the model.

Content

No source excerpt is available for this finding.