ClawHub
Back to skill

Security audit

Portfolio Risk Manager (No Margin)

Security checks for vulnerabilities and agentic risk

Overview

This skill provides disclosed portfolio risk-planning guidance and does not run code, access accounts, place trades, or persist changes.

Before installing, understand that the skill may automatically provide portfolio-planning guidance when the agent thinks it is relevant. Treat its outputs as planning support, verify assumptions such as monthly cash inflow and holdings data, and do not treat generated target weights as broker orders or personalized financial advice without your own 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill enables implicit invocation without defining narrow trigger conditions, so it may activate in contexts the user did not clearly intend. Because this skill provides portfolio and risk-management guidance, accidental activation could inject financial recommendations or assumptions into unrelated conversations, creating confusion or inappropriate advice.

Content

No source excerpt is available for this finding.