Back to skill

Security audit

rails-expert

Security checks for vulnerabilities and agentic risk

Overview

This Rails helper skill is a normal development guidance artifact with a minor Rails version mismatch, not a security concern.

This skill appears safe to install for Rails development assistance. Users should be aware that its documentation mixes Rails 8.1 and Rails 7 terminology, so verify version-specific advice before applying generated changes to a project.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (1)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest and opening documentation present the skill as a Rails 8.1 expert, yet the checklist and feature sections explicitly focus on 'Rails 7.x' and 'Rails 7 features'. This is an active contradiction in the skill's own documentation about its target platform and expertise scope.

Content

No source excerpt is available for this finding.