Back to skill

Security audit

Arbitrage

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed arbitrage-analysis helper that stores limited local notes and does not request credentials, trade execution, or hidden network access.

Before installing, be comfortable with the skill keeping local notes in ~/arbitrage/. During setup, choose a narrow activation preference if you only want it used when you explicitly ask for arbitrage analysis. Do not provide exchange keys, wallet secrets, or broker credentials; the skill says it does not need them.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The template leaves activation criteria blank, which can cause the skill to be invoked too broadly or without clear user intent boundaries. In a skill that persists files and tracks market-related preferences, ambiguous triggering increases the chance of unintended activation, unnecessary data retention, or acting on loosely related financial prompts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The setup instructions ask to 'Clarify when this skill should activate' but provide overlapping and contradictory options such as 'whenever the user mentions arbitrage' and 'only when the user asks directly.' This does not define a concrete trigger boundary and risks unintended invocation because ordinary discussion of arbitrage-related topics could activate the skill without a clear constraint or negative examples.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill instructs creation and maintenance of local files under the user's home directory without any explicit disclosure or consent step. While the actions are limited and not overtly dangerous, silent persistence can surprise users, create privacy concerns, and normalize filesystem writes without clear awareness.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.