ClawHub
Back to skill

Security audit

Ceo Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a plain prompt-only executive assistant skill, but its very broad triggers and vague autonomous-execution language make it worth user review before installation.

Install only if you want a broad executive workflow prompt to activate often. Use extra caution if your agent has tools that can send messages, change business records, access private files, or make commitments; require explicit confirmation for those actions.

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)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger keywords are extremely generic business terms like 'plan', 'review', 'goal', and 'project', which are common in ordinary conversations and likely to cause unintended skill activation. In a powerful executive assistant skill, accidental invocation can redirect conversations, override user expectations, or cause the agent to adopt a more autonomous workflow in contexts where that behavior was not intended.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs the agent to 'execute work where possible' and to 'take action autonomously when appropriate' without defining approval gates for high-impact actions. In an executive-assistant context, this increases the risk of the model taking consequential business actions, producing authoritative-seeming decisions, or proceeding without sufficient user confirmation, especially if accidentally triggered by broad keywords.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.