ClawHub
Back to skill

Security audit

Eternal Meeting Extractor

Security checks for vulnerabilities and agentic risk

Overview

This skill locally reads a user-provided meeting transcript and extracts summaries, action items, decisions, attendees, and questions without network access, persistence, or hidden privilege use.

Installers should understand that this is a simple local transcript parser, not a full meeting assistant: it may over-trigger on meeting-related wording and some advertised output modes are incomplete, but it does not show hidden data collection or privileged behavior.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest description says the skill should be used when the user has meeting notes and wants items like 'summary generated' or 'follow-up tasks identified,' and lists triggers such as 'meeting notes' and 'what were the decisions.' These phrases are broad and lack explicit scope or exclusion conditions, which could cause unintended invocation for ordinary conversation about meetings rather than deliberate use of this specific skill.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The argument parser declares --format choices including markdown, which communicates to users that markdown output is supported. However, format_output only has a special case for json and otherwise falls back to plain text formatting, so markdown does not do what the interface implies.

Content

No source excerpt is available for this finding.