ClawHub
Back to skill

Security audit

App Builder

Security checks for vulnerabilities and agentic risk

Overview

This app-building skill is coherent overall, but it can steer agents toward production deployment without a clear user approval gate.

Install only if you want an agent to help build applications. Before using it, require explicit approval for dependency installs, external service setup, secrets or environment configuration, and especially any deployment or live URL publication.

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description contains broad activation language such as building apps, adding features, scaffolding, and planning implementations from natural-language requests. In an agent-routing environment, this can cause the skill to be selected for many generic software requests, increasing the chance of unintended execution of build, modification, or deployment workflows without sufficiently precise user intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The keyword matrix uses highly generic terms like 'api', 'backend', 'service', 'dashboard', and 'mobile' as project-detection signals. These terms are common in ordinary developer conversations, so the skill may activate on ambiguous requests and steer the agent into app-building actions that the user did not clearly request.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The workflow directs the agent to deploy and provide a live URL, and elsewhere encourages deploying early, but it does not require a clear user-facing warning or explicit consent for production-impacting actions. In practice, this could lead to unintended publication of code, infrastructure changes, spending, data exposure, or changes to a live environment when the user only wanted planning or local implementation help.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.