Back to skill

Security audit

portfolio-rebalancer

Security checks for vulnerabilities and agentic risk

Overview

This skill calculates portfolio adjustments locally without accessing accounts, placing trades, or sending data elsewhere.

Review calculated trades manually before acting. Supply current positive prices, targets totaling 100%, and every holding; assets omitted from targets are ignored. The examples do not calculate transaction fees, taxes, or trading restrictions. No account credentials are needed.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (1)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The code performs a related monitoring task, but it does not implement the declared primary function of calculating rebalancing trades. Its output only indicates whether rebalancing is needed. No undeclared resource access or unrelated side effects are evident.

Content

No source excerpt is available for this finding.