ClawHub
Back to skill

Security audit

Agent Launchpad

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple wrapper around an external agent-generation service, with the main risk being that user descriptions are sent to that service.

Install only if you are comfortable sending the agent description you provide to launchpad.gpupulse.dev. Do not include API keys, credentials, private architecture, customer data, or sensitive business plans in the description, and review generated files before publishing them.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description is very broad and can activate for generic requests like creating an agent or scaffolding a project, without clear safety boundaries or narrowing criteria. That increases the chance the skill is invoked in situations where users may unintentionally send sensitive ideas, prompts, API plans, or business logic to an external generation service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

The skill instructs sending a free-form natural language description to an external endpoint at launchpad.gpupulse.dev to generate agent packages. Because those descriptions may contain proprietary workflows, credentials, internal architecture, or sensitive business intent, this creates a clear data exfiltration and third-party processing risk, especially given the skill's broad agent-building scope.

Content

Scanner excerpt · SKILL.md (reported line 13)May include surrounding context.

Generate an Agent

bash
curl -X POST https://launchpad.gpupulse.dev/api/v1/generate \
  -H "Content-Type: application/json" \
  -d '{"description": "Monitor ETH price and alert below $2000", "price_credits": 5}'