ClawHub
Back to skill

Security audit

open-ralph

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently runs an autonomous coding loop, which can change repository files, but that behavior fits its stated purpose and is bounded by git, iteration limits, and review guidance.

Install this only if you are comfortable letting Ralph/OpenCode make repeated changes in the current repository. Use a clean git branch, keep max iterations modest, provide precise success criteria, and inspect the diff before merging or committing changes.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The description explains that the skill repeatedly executes a coding prompt until success criteria or iteration limits are met, but it does not explicitly warn up front that this process can repeatedly modify repository files. That omission can mislead users about the operational risk of autonomous writes, especially since the loop is designed to retry and continue across iterations.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill advertises itself for a wide range of common coding tasks without narrowing scope, approval requirements, or repository safety constraints. Because it launches an autonomous multi-iteration code-modifying loop, broad invocation criteria increase the chance it will be triggered in inappropriate contexts and make repeated unintended changes to a repository.

Static analysis

No suspicious patterns detected.