Back to skill

Security audit

lgpd-legacy-retrofit

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: its checks found no executable files and treated the one persistence alert as likely a false positive, though some referenced paths were unavailable for review.

The verdict is benign, but confidence is medium and the scan was partial: nine local path references could not be resolved. Consider this uncertainty when deciding whether to install.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 16)May include surrounding context.

md
Inspecione sistematicamente:
1. **Modelos de dados e migrations** (`prisma/schema.prisma`, SQL, ORM models)
2. **Rotas, controllers, Server Actions e jobs assíncronos**
3. **Dependências, SDKs mobile/web e variáveis de ambiente** (`package.json`, `app.json`, `Info.plist`, `AndroidManifest.xml`, `.env.example`)
4. **Cookies, trackers, pixels e logs de aplicação/APM** (verificar vazamento de PII em `console.log`, Sentry, Datadog)
5. **Fluxos de autenticação, consentimento e exclusão de conta existentes**
6. **Infraestrutura como código (IaC)** — regiões de nuvem, criptografia de volumes/buckets, retenção de backups