Back to skill

Security audit

Trading System Pro

Security checks for vulnerabilities and agentic risk

Overview

This skill presents high-impact automated trading capabilities but does not define safeguards, confirmations, or limits for actions that could affect real funds.

Review carefully before installing. This package does not show malicious code, but its description could steer an agent toward live financial trading without documented safeguards; only use it if you can enforce paper-trading defaults, explicit per-order confirmation, broker permission limits, and clear separation between analysis and execution.

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
  • 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 (2)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The description promotes automated trade execution across broker and exchange integrations but omits any warning that use of the skill could place live orders or affect user funds. In a financial context, failing to disclose this risk is dangerous because users or calling agents may treat the skill as informational analysis when it may trigger irreversible monetary actions and losses.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises a very broad set of high-risk financial capabilities, including market scanning, automated trade execution, risk management, and portfolio balancing, without defining when it should activate or what user phrasing should invoke it. In an agent environment, vague activation boundaries can cause the skill to be selected in inappropriate contexts, increasing the chance of unauthorized or unsafe trading-related guidance or actions.

Content

No source excerpt is available for this finding.