ClawHub
Back to skill

Security audit

Meeting Minutes Pro

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward meeting-minutes template with no executable code, hidden behavior, persistence, or credential access.

Before using it with confidential meetings, confirm who may receive the minutes, where they should be stored, and whether names, recordings, transcripts, or sensitive business details should be redacted. The skill itself does not add hidden access or automation.

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
  • 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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs publishing minutes and references handling recordings, transcripts, shared drives, repos, tickets, and email, but it does not require a privacy check, minimization step, or warning before distributing potentially sensitive internal meeting content. This can lead to unintentional disclosure of confidential business information, attendee data, or sensitive discussion details to broader audiences or less secure systems.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest presents the display name and description exclusively in Chinese, with no indication that users can choose another language or that the skill is intentionally limited to a Chinese-speaking region. This can violate language/locale policy where skills should not force a specific language without user opt-in or clear justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.