ClawHub
Back to skill

Security audit

Meeting

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed meeting-assistant skill that drafts notes, minutes, and follow-up actions without shipping executable code or hidden persistence.

Before installing, make sure you are comfortable letting the skill process meeting notes, transcripts, calendar context, and connector-visible meeting data. Review all generated minutes, tasks, and destinations before authorizing any sync or distribution, especially when notes contain confidential decisions or dissent.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The example normalizes syncing post-meeting outputs to a Lark Group immediately after generating notes, but it does not mention verifying recipient scope, data sensitivity, or obtaining explicit approval beyond a vague authorization prompt. In a meeting assistant context, outputs may contain internal decisions, dissent, timelines, or confidential project details, so presenting external/group sync as routine can encourage unsafe sharing behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger phrases are generic enough to match a wide range of normal meeting-related requests, which can cause the skill to activate outside its intended scope. In an agent ecosystem, broad activation increases the chance of unintended interception of user tasks, misrouting, or over-collection of sensitive meeting content such as notes, decisions, and commitments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.