Back to skill

Security audit

A Stock Trading Assistant

Security checks for vulnerabilities and agentic risk

Overview

This A-share stock assistant is not clearly malicious, but it warrants review because it gives actionable trading guidance from unauthenticated market data and stores user alert/watchlist information.

Before installing, treat this as an unregulated market-analysis helper rather than a financial adviser. Be aware that it may save your alert/watchlist interests locally, and verify prices and any buy/sell or position-sizing suggestions against a trusted brokerage or market-data source before acting.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/fetch_stock.py:113
Finding

Unauthenticated HTTP Allows Manipulation of Financial Market Data

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions are written in mixed Chinese and English and rely on descriptive phrases rather than precise boundaries, making invocation ambiguous. This ambiguity can lead to accidental activation or inconsistent behavior across user inputs, which is risky for a skill that claims real-time market data access and can influence trading decisions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs persisting user alert settings to a local file without an explicit user-facing notice or consent flow. Even if the stored data seems limited, watchlist entries and price alerts reflect user investment interests and behavior, so silent retention creates a privacy risk and may expose sensitive financial preferences to other processes or future sessions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The document gives concrete buy/sell, position-sizing, and market-timing guidance such as '可做多', '买入信号', '卖出信号', and recommended仓位, but it does not include any warning that the material is educational or that investing involves risk. In an agent skill context, users may reasonably treat this as actionable financial advice, increasing the chance of harmful decisions and potential compliance or trust issues.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The trigger conditions are written in mixed Chinese and English and rely on descriptive phrases rather than precise boundaries, making invocation ambiguous. This ambiguity can lead to accidental activation or inconsistent behavior across user inputs, which is risky for a skill that claims real-time market data access and can influence trading decisions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The natural-language content forces a specific language/locale throughout the file. The policy allows locale constraints only when the skill offers user choice or clearly documents a justified regional limitation, neither of which appears here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file contains user-facing instructions exclusively in Chinese and does not state that the language is optional or region-specific. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The request header hard-codes "Accept-Language: zh-CN,zh;q=0.9", which imposes a specific locale preference. Under the policy, language or locale constraints should be optional or clearly justified; this file does not offer user opt-in or explain why Chinese locale is required.

Content

No source excerpt is available for this finding.