Back to skill

Security audit

Charlie Munger Investing Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Charlie Munger thinking and investing-philosophy skill with no executable code, persistence, credential access, or hidden system changes.

Installers should understand that this skill may answer in a Munger-style investing and decision-making frame. Do not treat its investment principles as personalized financial, legal, or tax advice, and consider narrowing triggers if you do not want generic topics like mental models or inversion to activate 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
  • 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 (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill gives investment-oriented guidance such as concentration, intrinsic value, margin of safety, and portfolio decision criteria, but does not warn users that this is educational content rather than financial advice. In practice, users may treat the skill as actionable investing guidance, which can influence real financial decisions without suitability, jurisdictional, or risk disclosures.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list includes broad terms like "mental models," "inversion," "rationality," and "Munger" that can appear in many unrelated conversations. This can cause the skill to activate outside its intended context, steering the agent into unsolicited investing or decision-making guidance and increasing the chance of inappropriate or misleading responses in general conversations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes generic phrases such as "mental models," "multidisciplinary thinking," and "inversion" that are not uniquely tied to Charlie Munger. This can cause the skill to activate in unrelated contexts, leading to unintended routing, persona bleed, or interception of user requests meant for other skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The manifest sets the skill language to "en", which is a locale/language constraint expressed in configuration. There is no indication here that users can opt into another language or that English-only behavior is specifically justified as a region- or compliance-bound requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file is subject to natural-language policy checks. At L234, the heading uses Chinese characters followed by an English translation, which imposes mixed-language content without any stated user opt-in or justification for the locale choice.

Content

No source excerpt is available for this finding.