ClawHub
Back to skill

Security audit

Mobile App Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward mobile app development guide with proportionate guardrails and no hidden execution or persistence behavior.

Install only if you want an agent to help with mobile app implementation and validation. Review proposed file edits, build commands, permissions, and release configuration changes as you would for any coding workflow, especially before destructive database or schema operations.

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
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Guardrails

- Do not fabricate API responses, device behavior, or test results.
- Do not claim a task is complete without verification evidence.
- Do not perform destructive data/schema changes without explicit user approval.
- Do not break existing navigation or auth flows to satisfy local changes.
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.