ClawHub
Back to skill

Security audit

Projects

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local project-notes helper with disclosed, scoped filesystem writes and no evidence of network access, code execution, credential handling, or deceptive behavior.

Before installing, be aware that ordinary project discussions may cause the agent to help organize or record project information in local notes. Use clear commands and ask for confirmation if you do not want casual mentions saved as project data, especially for client names, rates, contacts, or deadlines.

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
92% confidence
Finding
The skill uses very broad natural-language triggers such as 'User mentions a project' and 'User adds tasks', without clear invocation boundaries or explicit user consent before creating folders and writing notes. This can cause the agent to activate on ordinary conversation and perform unintended filesystem actions, leading to accidental data creation, context pollution, or privacy issues from recording user statements as project data.

Static analysis

No suspicious patterns detected.