ClawHub
Back to skill

Security audit

trading-plan-generator

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent trading-plan skill that uses a disclosed Finskills API key and market-data calls, with privacy cautions around financial details but no evidence of hidden execution, persistence, or data exfiltration.

Install only if you are comfortable using the Finskills service and storing a FINSKILLS_API_KEY. Share approximate account size or risk limits where possible, avoid unnecessary personal financial details, and treat generated plans as educational analysis rather than financial advice.

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)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The README states that the skill is powered by live Finskills API data and requires an API key, but it does not clearly warn users that their prompts and trading-related inputs may be transmitted to an external third-party service. Because users may share account size, risk tolerance, positions, and ticker intentions, this omission can lead to unintentional disclosure of sensitive financial information and surprise data sharing.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The activation guidance includes generic phrases like asking for a 'trade plan', 'entry point', or 'stop loss' that can easily overlap with normal financial discussion. This can cause the skill to trigger when a user did not intend portfolio-style planning, increasing the chance that the agent collects extra financial context or provides more specific trading guidance than necessary.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly asks for account size and maximum risk per trade, which are sensitive financial details, but it does not warn users to minimize disclosure or explain why the data is needed. In the context of a trading-planning skill, this creates unnecessary privacy risk because users may overshare portfolio information without informed consent.

Static analysis

No suspicious patterns detected.