Back to skill

Security audit

投资者认知基石书单

Security checks for vulnerabilities and agentic risk

Overview

This is a static investment reading-list skill with no executable behavior, but users should treat its finance content as educational rather than personal advice.

Install only if you want educational summaries of investment classics and concepts. Do not treat the skill's output as personalized financial, legal, or tax advice, and be cautious if an agent uses it to answer questions about what to buy, sell, or allocate without asking for context and limits.

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
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill presents investment frameworks, valuation methods, and decision heuristics without any warning that the material is educational and not personalized financial advice. In an investment context this omission is risky because users may reasonably rely on the content for real financial decisions, increasing the chance of harmful misuse or regulatory/compliance issues if the agent appears to recommend trades or strategies.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger examples are very broad (e.g. common questions about investment basics, models, or valuation), which can cause the skill to activate in many ordinary finance conversations without clear user intent. In the context of investment content, over-broad invocation increases the chance the agent provides actionable-seeming financial guidance when the user may only want general discussion, especially because the skill does not tightly limit itself to book summaries or educational framing.

Content

No source excerpt is available for this finding.