ClawHub
Back to skill

Security audit

meeting-notes-formatter

Security checks for vulnerabilities and agentic risk

Overview

This is a simple meeting-notes formatting skill that only asks the assistant to restructure user-provided notes and does not add tools, persistence, network access, or write behavior.

Install this if you want an assistant shortcut for restructuring meeting notes. As with any note-processing skill, avoid pasting sensitive meeting content unless you are comfortable having the assistant process it.

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

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The activation guidance includes phrases like "clean up notes" and a general condition of using the skill after meetings when notes are messy. In a markdown skill description, this is a vague trigger because it does not define boundaries, required context, or negative examples to distinguish this skill from other summarization or note-editing tasks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.