ClawHub
Back to skill

Security audit

Howard Marks' Second Level Thinking

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Markdown-only framework for structured investment analysis, with no hidden code or privileged behavior found.

Use this as an investment research and reasoning framework, not as financial advice. Because it encourages current market research, users should verify cited data and sources before making any investment decision.

A.I.G

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

SkillSpector

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 (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The description says to use the skill whenever the user is analyzing an investment opportunity, evaluating a thesis, asking about market attractiveness, risk/reward asymmetry, market cycles, or contrarian positioning. These triggers are expansive and lack clear boundaries or negative examples, making it ambiguous when the skill should activate versus when a general finance discussion would not qualify.

Static analysis

No suspicious patterns detected.