ClawHub
Back to skill

Security audit

Business Canvas

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed business-planning helper that reads project context and writes structured canvas documents, with no evidence of hidden execution, exfiltration, or persistence.

Install this if you want an agent to inspect your project context and help produce business-modeling documents. Review the generated docs before sharing them, especially because they may summarize product strategy, pricing, competitors, and assumptions inferred from your repository.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes very broad phrases such as "business model," "analyze business model," and startup-evaluation phrasing that can match many general conversations, causing the skill to activate outside the user's specific intent. Unintended invocation can lead to unnecessary repo scanning, file creation under docs/business/, and irrelevant guidance, which is a security and safety concern because skills should activate only with clear, narrow user intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.