ClawHub
Back to skill

Security audit

System Resource Report

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently reads local Linux resource metrics and does not show evidence of modification, persistence, credential handling, or network activity.

Install only if you are comfortable with the agent seeing local machine health information and top process command lines, which may include sensitive command arguments. The skill appears read-only and purpose-aligned.

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 (1)

Vague Triggers

Low
Confidence
87% confidence
Finding
The manifest and body say to use the skill when the user asks about 'system resources,' 'resource usage,' or 'machine health/resource summaries,' which are fairly broad phrases without explicit boundaries or exclusion examples. This could cause unintended invocation for generic troubleshooting or status questions that are not specifically requesting this report.

Static analysis

No suspicious patterns detected.