ClawHub
Back to skill

Security audit

Board Reporting Framework

Security checks for vulnerabilities and agentic risk

Overview

This is a simple board-reporting template skill; it is purpose-aligned but users should explicitly approve any sensitive business data sources before using it.

Install only if you are comfortable using this as a reporting framework. Before asking an agent to generate a deck or flash report, name the approved data sources, reporting period, and company/entity, and review outputs carefully because board materials may contain confidential financial, customer, and strategy information.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The README suggests invoking the skill with phrases like "Prepare the Q1 board deck" or "Generate the monthly flash report," but it does not define whether these are the only triggers, what context they apply in, or any exclusion conditions. These phrases are plausible everyday work requests and could overlap with unrelated reporting tasks, increasing the risk of unintended skill activation.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The usage section uses broad prompts like 'Prepare the Q1 board deck' and 'Generate the monthly flash report for January' without defining data sources, authorization scope, or when the skill should activate. In an agentic environment, this can cause overbroad invocation and unintended access to sensitive financial, customer, or board materials because the skill implies it will 'pull your data' automatically.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill states that it will 'pull your data' to generate board materials, but it provides no warning or safeguards for handling highly sensitive business information such as financials, runway, customer churn, pipeline, regulatory status, or board discussions. Because board reporting often includes confidential and market-sensitive data, this omission increases the risk of unauthorized collection, excessive processing, or disclosure by the agent.

Static analysis

No suspicious patterns detected.