ClawHub
Back to skill

Security audit

Medici Investments — Position Sizer

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate stock position-sizing calculator, but it runs a local script that saves sensitive account and trade details to report files by default without clear upfront disclosure.

Install only if you are comfortable with local report files containing portfolio size and planned trade details. Run it in a folder where saved reports are acceptable, avoid synced or shared directories for sensitive trades, and do not provide brokerage credentials because the skill does not need them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill declares no tools or permissions, yet its instructions direct the agent to execute a shell command (`python3 ...`) and imply script-based processing. This mismatch is dangerous because it can bypass governance expectations around what the skill is allowed to do, leading to unauthorized command execution or filesystem interaction if an agent trusts the prose over the metadata.

Vague Triggers

Medium
Confidence
76% confidence
Finding
The implicit triggers are broad enough that the skill may activate for general investing or risk-management discussions without a clear request for position sizing. Over-broad activation can cause the wrong skill to run, increasing the chance an agent follows unnecessary shell/script instructions or provides mismatched financial guidance in contexts where the user did not ask for it.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.