ClawHub
Back to skill

Security audit

Stanley Druckenmiller Investing Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed macro-investing persona skill, but it can present very aggressive leverage and position-sizing guidance without enough safety framing.

Install only if you want an aggressive, educational macro-trading persona. Treat its allocation, leverage, and market-positioning language as historical or conceptual commentary, not personal financial advice, and do not connect it to trading actions without separate safeguards and professional review.

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 (3)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill gives explicit high-risk trading guidance such as concentrated bets, 50-100% sizing, and even '200%' Soros-level exposure without clear safety disclaimers, suitability limits, or warnings about loss, leverage, and financial harm. In an agent setting, this can be surfaced as actionable advice to users and may encourage dangerous real-world financial behavior, especially because the surrounding language is confident and prescriptive.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list includes broad terms like 'macro investing,' 'stablecoins,' 'AI investing,' 'position sizing,' and 'cutting losses,' which are common in ordinary finance conversations. This increases the chance the skill activates outside narrow intent, causing the agent to inject aggressive trading and leverage-oriented guidance into contexts where the user did not request it.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrase "Soros" is a broad standalone surname associated with many contexts beyond this specific skill, so it can cause unintended activation when users mention Soros in unrelated financial, political, or historical discussions. In an agent system, overbroad triggers can route conversations to the wrong skill, causing misleading responses, inappropriate context injection, or unexpected behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.