ClawHub
Back to skill

Security audit

Investment Risk Scanner (Buffett + Porter Framework)

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only investment analysis checklist with no code execution, persistence, credential use, or hidden access behavior.

Before installing, understand that this skill provides a strongly opinionated investment risk framework with built-in case judgments that may be dated or unsourced. Verify current financial data independently and do not treat its output as personalized financial advice.

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 (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger phrases are broad enough to activate on common, ambiguous investment-related queries such as legitimacy checks or stock-buying questions. This can cause the skill to intercept conversations outside its intended scope, increasing the chance of unsolicited financial-risk judgments, over-application of its heuristics, and user confusion about whether they are receiving general discussion or structured investment analysis.

Natural-Language Policy Violations

Low
Confidence
75% confidence
Finding
The file includes Chinese terms and examples such as "迪链-type tools" inline with English guidance, and this pattern continues throughout the document. Because the skill does not state whether outputs should follow the user's language preference or provide an opt-in for Chinese terminology, it risks imposing a mixed locale style unexpectedly.

Static analysis

No suspicious patterns detected.