ClawHub
Back to skill

Security audit

LLM Wiki

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent local Markdown wiki helper, with expected file-writing behavior and no evidence of hidden network access, credential use, persistence, or destructive intent.

Installers should treat this as a local knowledge-base maintainer: point it only at vaults you want the agent to read and edit, review changes to important notes, and use --force only when you are comfortable replacing the starter scaffold files in the target directory.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill clearly directs the agent to create and update local Markdown files, logs, indexes, and wiki pages, which implies file-write capability, but it does not declare any explicit tool scope or permission boundary. This increases the chance that an agent runtime grants broader write access than intended, enabling unintended modification of user files or workspace content during ingest, reindex, or lint operations.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The Quick Start instructs users to run an initialization script with a `--force` option that overwrites existing scaffold files, but the skill does not prominently warn about data loss or clarify exactly what may be replaced. In a knowledge-management context, accidental overwrites could destroy curated notes, schema files, or logs, especially if the target path is mis-specified or reused.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
The section framing requests that should trigger the skill provides examples exclusively in Chinese, which may imply a language-specific invocation pattern without stating that other languages are also supported. This can create an avoidable language policy ambiguity if the skill is intended for broader use.

Missing User Warnings

Low
Confidence
81% confidence
Finding
This code file performs file writes throughout the target directory and the --force flag enables overwriting existing scaffold files. While actions are printed after execution, there is no pre-action confirmation, warning comment, or other explicit disclosure near the overwrite option that existing files will be replaced.

Static analysis

No suspicious patterns detected.