ClawHub
Back to skill

Security audit

Chief Of Staff Onboarding Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a coaching-only Chief of Staff onboarding skill with no code, tools, persistence, or hidden data access.

Safe to install for CoS onboarding guidance. Users should keep company-sensitive materials under their own control and confirm the skill is being used in a Chief of Staff context if it activates on generic workplace phrases.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger list includes very broad terms such as "first 90 days," "principal," and "primary," which can plausibly appear in many unrelated workplace conversations. This can cause the skill to activate outside its intended Chief-of-Staff context, leading to irrelevant or inappropriate guidance being injected into user interactions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The guidance says to "match the CEO's communication style," which can be read to require the assistant to adopt a principal's preferred language or locale automatically. Because no user choice or opt-in is mentioned, this may conflict with language/locale policy if applied rigidly.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.