ClawHub
Back to skill

Security audit

Board Of Mentors

Security checks for vulnerabilities and agentic risk

Overview

This is a mentorship-prompt skill with broad advisor personas but no code execution, data access, persistence, or hidden system changes.

Install only if you want the agent to answer founder and operator advice requests through mentor personas. For legal, financial, or wellness topics, treat the output as general guidance and use qualified professionals for decisions.

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 (3)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The phrase 'When a user needs domain expertise' is very broad and could match many ordinary conversations, without defining specific trigger phrases or boundaries for when this skill should activate. The README does not provide exclusion conditions or narrower context to prevent unintended invocation.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill activates on very broad categories like growth, sales, product, legal, finance, and wellness, which are common advice topics in general conversation. That can cause the skill to trigger when the user did not explicitly request a mentor persona, leading to unwanted instruction takeover, reduced relevance, and potentially unsafe overreach into sensitive domains such as legal or financial guidance.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The keyword-based routing maps common words directly to mentors without contextual validation or conflict resolution, so ordinary terms like 'product', 'team', 'contract', or 'stress' may spuriously invoke a persona. In practice this can misclassify user intent, cause inconsistent behavior, and amplify risky guidance in sensitive domains by presenting advice with unwarranted authority.

Static analysis

No suspicious patterns detected.