ClawHub
Back to skill

Security audit

ExpertPack

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Markdown guidance package for creating and using ExpertPacks, with no executable payload or hidden persistence.

Installers should understand that this skill helps agents read, create, and index ExpertPack directories. Only point RAG at packs you intend the agent to use, and review any optional companion tools or Obsidian plugins separately before installing them.

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list includes broad, generic phrases such as 'knowledge pack', 'obsidian vault', and 'esoteric knowledge' that can match many unrelated user requests. This can cause the skill to activate in contexts where it was not intended, increasing the chance of inappropriate guidance, context pollution, or accidental invocation of adjacent tooling/workflows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.