Back to skill

Security audit

Multi-Dimensional Trading System

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only trading analysis framework with clear data-source safeguards and no code, persistence, credential access, or hidden execution behavior.

Install only if you want an assistant to provide structured technical trading analysis. Do not treat its outputs as investment advice, and reject any entry, stop-loss, or take-profit levels unless the assistant cites a current, verifiable market data source.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

Several example triggers are phrased as normal finance questions like 'Where is the support level for ETH?' or 'Is BYD a good entry now?', which are common conversational requests rather than explicit skill calls. If these examples reflect activation behavior, the skill may intercept broad classes of financial queries and push users into a specific prompt-defined decision framework without clear consent or boundaries.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger keywords are broad finance terms such as 'day trading', 'Fibonacci', 'support level', and 'resistance level', which can easily appear in ordinary market discussion. In an agent environment, this can cause unintended skill activation and steer the assistant into producing structured trading recommendations when the user did not explicitly request this workflow, increasing the risk of inappropriate financial guidance or context hijacking.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation logic uses broad intent phrases such as generic requests for whether to enter, trade, or operate on a specific asset, which can match normal financial conversation beyond the intended niche. This can cause the skill to trigger unexpectedly and steer the assistant into giving highly specific trading instructions, increasing the risk of inappropriate or non-contextual financial guidance.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes broad, common trading terms such as 'support level', 'resistance level', and generic market-analysis language, which can cause the skill to activate outside the author's intended scope. In this context, unintended activation is more dangerous because the skill is designed to generate structured trading recommendations, so accidental invocation could steer unrelated conversations into high-stakes financial guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file instructs the agent to "strictly follow" a fixed English report template and execution format, but does not mention adapting to the user's preferred language or offering locale choice. That can violate a language/locale policy where users should not be forced into a specific language without opt-in.

Content

No source excerpt is available for this finding.