ClawHub
Back to skill

Security audit

Jarvis Refactor Planner 01

Security checks for vulnerabilities and agentic risk

Overview

This is a simple planning-only skill for refactor workflows and does not request privileged access, persistence, network use, or code execution.

This skill is reasonable to install for refactor planning and structured development workflows. Be aware that its trigger language is broad, so it may activate for ordinary planning tasks; users who want tighter routing may prefer a narrower description, but no security-sensitive behavior was found.

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
  • 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)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The description says to use the skill for "development work that needs repeatable steps, quality gates, and practical outputs," which is broad and could match many ordinary software-assistance requests. It does not clearly define boundaries or exclusion conditions for when this skill should activate versus other planning or coding skills.

Vague Triggers

Low
Confidence
87% confidence
Finding
The phrase "Deliver a concrete, reusable workflow for development tasks" is an open-ended capability statement that could apply to a wide range of routine requests. Because it does not specify trigger phrases, task boundaries, or exclusions, it may contribute to unintended invocation.

Static analysis

No suspicious patterns detected.