Back to skill

Security audit

macd-stock-screener

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed stock-screening script that fetches public market/comment data and writes reports, with dependency and wording cautions but no evidence of hidden or harmful behavior.

Install and run this in a virtual environment, consider pinning dependencies before use, and expect outbound requests to public financial data sources plus local report files. Ask for confirmation before running it on vague stock-picking requests, and treat the generated 'sentiment analysis' report as a simple public-comment summary rather than real sentiment scoring.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:87
Finding

Unpinned Third-Party Dependencies Permit Supply-Chain Compromise

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill advertises executable behavior that writes output files, but it does not declare any explicit tool scope or permission boundaries. This can cause the agent runtime to invoke file-writing behavior without clear least-privilege constraints, increasing the chance of unintended filesystem modifications or policy bypass during execution.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The overview describes stock screening and sentiment collection, but it does not clearly warn users up front that the skill will access external data sources and scrape forum-like content. Without explicit disclosure, users may unknowingly trigger outbound network activity and collection of third-party content, which creates consent, privacy, and compliance risks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases include very generic terms like “选股”, which can match many ordinary conversations and cause the skill to run unexpectedly. Because the skill performs large-scale market scanning, network scraping, and file generation, accidental invocation can lead to unintended external requests, resource consumption, and user-surprising actions.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

collect_guba_sentiment 的注释称其“采集东方财富股吧舆情数据”,并提到验证码检测与放慢访问速度,给人的语义是面向指定股票抓取股吧内容;但实际实现只是调用 ak.stock_comment_em() 后按代码筛选一行摘要字段,既没有显式访问该股票股吧帖子列表,也没有实际验证码检测流程。这使注释对实现能力形成了误导。

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

函数文档与输出标题多次声明生成“股吧舆情情感分析报告”,但实现仅把 stock_comment_em() 返回的“最新动态/相关资讯/评论数”原样写入 Markdown,没有任何情感分类、打分或分析逻辑。这属于文档/命名对能力的主动暗示,与实际代码行为存在明显偏差。

Content

No source excerpt is available for this finding.