Back to skill

Security audit

Lovable Dev

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown Lovable development helper; it describes expected app-building, Supabase, GitHub, and deployment workflows without bundled code or hidden execution.

Before using generated Supabase, GitHub, or deployment output, review database policies, auth settings, storage rules, repository visibility, secrets, and hosting targets. The skill itself appears informational and purpose-aligned, but those connected services can expose data or code if configured carelessly.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill promotes automatic creation of database tables, RLS policies, authentication, and file upload features without telling users to review security-sensitive backend changes. This is dangerous because autogenerated backend configuration can introduce overly permissive access controls, insecure auth flows, or unsafe storage exposure that users may trust without verification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises automatic GitHub syncing and one-click deployment, including publishing to hosted domains, but provides no warning that source code may be transferred to third-party services or publicly deployed. In an agent context, this can cause unintended code exposure, accidental publication of sensitive content, or unauthorized external actions if users do not realize these operations leave the local environment.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.