Back to skill

Security audit

华尔街股票分析系统

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent stock-analysis prompt that fetches market data for reports and does not install code, persist changes, or access private credentials.

Before installing, be aware that the skill may query external finance data providers and will produce investment-style analysis that should not be treated as personalized financial advice. Use it for research support, verify important figures independently, and clarify the stock code when invoking it.

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
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire skill is written to operate in Chinese and specifies Chinese trigger phrasing, with no indication that users may choose another language. Under the language/locale policy rule, forcing a specific language without opt-in is a natural-language policy concern unless the locale constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation trigger uses open-ended wording like 'or similar instructions', which can cause unintended invocation from loosely related user messages. In a skill that performs external data fetching and produces investment-style judgments, ambiguous activation increases the chance of accidental execution and user confusion about when third-party calls and analysis will occur.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill states it will fetch real-time stock data from third-party sources but does not clearly warn the user that external network requests will be made. This reduces transparency and informed consent, especially in environments where outbound requests, data provenance, or compliance requirements matter.

Content

No source excerpt is available for this finding.