ClawHub
Back to skill

Security audit

Executive

Security checks for vulnerabilities and agentic risk

Overview

This is a plain executive-assistant skill, but it asks the agent to proactively monitor sensitive messages, meetings, tasks, and external intelligence without clear opt-in boundaries.

Install only if you want an agent to act as a proactive executive assistant. Before enabling heartbeat or briefing behavior, restrict which inboxes, calendars, task files, metrics, and news sources it may read, and require approval before sending messages or sharing briefings beyond the user.

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

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises a very broad activation scope for 'C-level executives, ministers, and leaders' and then authorizes proactive behaviors like scanning messages, reviewing meetings, checking tasks, and gathering external intelligence. Without narrow triggers, role boundaries, or explicit consent gates, this can cause the agent to activate in sensitive contexts and access or synthesize high-value organizational information unnecessarily.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.