Back to skill

Security audit

Benjamin Graham Investing Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Benjamin Graham investment-analysis persona skill with no code execution or hidden system access, though users should treat its buy/hold/avoid language as educational rather than personalized financial advice.

Install only if you want educational value-investing commentary. Do not treat its buy/hold/avoid output as personalized financial, legal, or tax advice, and verify current market data and your own risk tolerance before acting.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to analyze stocks and provide a clear buy/hold/avoid recommendation, but it does not include any warning that the output is educational in nature and not personalized financial advice. Because the skill is framed as Benjamin Graham and provides concrete investment criteria, users may over-trust the output and act on it in ways that affect their finances.

Static analysis

No suspicious patterns detected.