ClawHub
Back to skill

Security audit

Rag Chunking Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill gives RAG chunking guidance and read-only document profiling commands, with no evidence of hidden execution or persistence.

This skill is reasonable to install for RAG chunking work. Run its example commands only against the documentation corpus you intend to analyze, especially if your docs directory contains private or regulated content.

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

Medium
Confidence
91% confidence
Finding
The usage triggers are phrased as generic help requests rather than narrowly scoped invocations, which increases the chance that the skill activates during ordinary conversation unrelated to explicit RAG optimization tasks. That can cause unintended tool selection, confusing responses, or unnecessary command suggestions against local documentation directories when the user only wanted general advice.

Static analysis

No suspicious patterns detected.