ClawHub
Back to skill

Security audit

boardroom-advisor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent business-advice workflow, but it can activate proactively and send sensitive business context to an external model without a clear confirmation boundary.

Install only if you are comfortable with the agent using this workflow for business decisions. Before use, narrow activation to explicit phrases like 'consult the board' or require confirmation before gathering business context, creating files, spawning a sub-agent, or sending data to OpenRouter. Avoid providing confidential financial, customer, or strategy information unless you accept the external model provider's handling of that data.

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
91% confidence
Finding
The trigger list includes broad conversational phrases such as 'should I do X?' and 'get the board's view,' which can easily appear in normal dialogue without the user intending to invoke this skill. In combination with the skill's ability to gather business context, write files, and optionally call an external model provider, ambiguous activation raises the risk of unintended execution and data disclosure.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to run proactively whenever it 'identif[ies] the user is facing a major decision,' even without a clear request. That broad trigger can cause unsolicited invocation, unexpected context gathering, and unnecessary file creation or network use, which weakens user intent boundaries and can lead to confusing or privacy-invasive behavior.

Static analysis

No suspicious patterns detected.