ClawHub
Back to skill

Security audit

Learned from AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward note-making helper that clearly says it will save study notes and cheat sheets under a notes folder.

Install this only if you want AI chat material converted into saved local notes by default. Avoid giving it sensitive chats or private links unless you are comfortable with a subagent processing them and with source links being preserved in notes/; ask explicitly for inline output, no subagent, or a different save location when needed.

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to always save outputs into `notes/` by default, but it does not require explicit user confirmation before creating or modifying files in the workspace. That can cause unintended persistence of sensitive or unwanted content, especially when the user only asked for transformation or review rather than file-writing.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The workflow mandates writing both a main note and a cheat sheet to disk as part of normal execution, without an intervening confirmation step or warning about workspace side effects. In context, this makes the behavior more dangerous because file creation is presented as non-optional and automatic across all uses of the skill.

Static analysis

No suspicious patterns detected.