ClawHub
Back to skill

Security audit

McKinsey-Style Meeting Brief Copilot

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain-text meeting-prep assistant with no executable code or hidden access, though users should review inferred assumptions in its outputs.

This skill is reasonable to install for meeting preparation. Because it may summarize email threads and meeting notes and may infer missing context, avoid pasting sensitive material unless you are comfortable having the agent process it, and review generated briefs for assumptions before using them professionally.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
- what to confirm afterward

### If the user provides very little context
Do not refuse.
Infer the likely meeting type and provide the most useful brief possible.

## Quality bar
Confidence
85% confidence
Finding
Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

Vague Triggers

Medium
Confidence
92% confidence
Finding
This plain-text file consists of sample invocation phrases such as 'help me prepare' style meeting and email requests that overlap with common workplace language. It does not define when the skill should activate, provide a bounded trigger list, or include exclusion examples, which makes unintended invocation more likely.

Static analysis

No suspicious patterns detected.