Back to skill

Security audit

Stock Analysis Expert

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed A-share stock analysis skill with financial-advice caveats, but it contains only Markdown instructions and no hidden execution, persistence, or data access behavior.

Install only if you want Chinese-language A-share research assistance. Treat its ratings, target prices, stop-loss levels, accuracy claims, and buy/sell signals as informational analysis, not professional financial advice or automated trading guidance; verify market data and consult a qualified advisor before making investment decisions.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description and body of the skill are written entirely in Chinese and present the skill as the default interaction mode, with no indication that users can choose another language. Under the policy, a skill that forces a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest states the output is a professional stock analysis report containing investment recommendations, and the example output includes a strong recommendation, target price, and stop-loss. However, the final risk disclaimer says the skill is only for reference and does not constitute investment advice, which directly conflicts with the stated output and example behavior.

Content

No source excerpt is available for this finding.