ClawHub
Back to skill

Security audit

MBB Strategist

Security checks for vulnerabilities and agentic risk

Overview

This is a consulting-framework prompt skill with broad activation wording, but it does not request tools, credentials, persistence, execution, or data access.

Installers should expect this skill to steer business-related answers into consulting frameworks and named business personas. It is reasonable to use for strategy, GTM, market analysis, pricing, and planning work, but users should treat financial projections, market intelligence, and executive recommendations as draft analysis that needs source checking and professional judgment.

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
Confidence
94% confidence
Finding
The skill description claims applicability to 'any business or project,' which creates an overly broad activation scope. In an agent environment, this can cause the skill to trigger for a very wide range of prompts, potentially overriding more specific or safer skills and increasing the chance of inappropriate persona adoption or strategy-style responses in contexts where they are not intended.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The invocation guidance says to use the skill whenever a user provides a business context, but 'business context' is undefined and extremely broad. This ambiguity can lead to over-activation, causing the agent to apply consulting frameworks and personas in situations where another skill or a neutral response would be more appropriate, reducing predictability and potentially affecting response safety or quality.

Static analysis

No suspicious patterns detected.