ClawHub
Back to skill

Security audit

Portfolio Tracker

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent portfolio tracker, but it can expose personal holdings through browser lookups and update local financial records under broad trigger wording.

Install only if you intend this skill to manage Vish's portfolio data. Use it with explicit update commands, review any proposed changes before they are written, and assume ticker lookups and related browsing activity may be visible to Yahoo Finance and the configured Chrome profile.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill description triggers on very broad phrases like stocks, portfolio, investments, or market updates, which can cause the agent to invoke this skill during ordinary financial conversations where the user did not request browser automation or file modification. In context, this is dangerous because the skill performs external browsing and local portfolio updates, so accidental activation can expose financial interests and cause unintended changes to local files.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill directs the agent to fetch live prices from Yahoo Finance for the user's holdings without disclosing that ticker symbols and browsing activity will be sent to a third-party service. In this context, the holdings file contains a specific person's portfolio, so repeated lookups can leak sensitive financial interests and patterns to an external provider.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The workflow instructs the agent to edit portfolio-tracker.md with new values but does not warn the user that local data will be modified. This creates a risk of silent or unexpected changes to user-managed financial records, especially if the skill is auto-invoked or run without explicit review.

Static analysis

No suspicious patterns detected.