Back to skill

Security audit

lgpd-dsar

Security checks for vulnerabilities and agentic risk

Overview

ClawScan gives this skill a benign verdict with medium confidence: the scanners report DSAR-related helpers and a broader child-protection compliance capability, while some referenced material was only partly inspected.

The verdict is benign, but review whether the broader child and adolescent compliance capability fits your needs. Two referenced materials were only partly inspected because of parser limits, so the scan does not establish that every part of the skill was fully assessed.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The SLA calculator directly supports the declared purpose, and erasure/retention planning is a reasonable supporting detail for DSAR handling. However, classifyMinorAgeRules implements broader child-protection and advertising-compliance policy beyond the declared DSAR scope, including LGPD Art. 14 and ECA Digital rules. This is a distinct undeclared capability, rather than merely representative or identity-verification handling. Missing endpoint and document-generation logic is not independently treated as a mismatch because only a code chunk was supplied.

Content

No source excerpt is available for this finding.

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
Não aplique a mesma regra de resposta imediata indistintamente a todos os agentes e modalidades. Consulte [`assets/dsar-sla.ts`](assets/dsar-sla.ts):

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

md
- Cálculo de SLA e disposição de retenção: [`assets/dsar-sla.ts`](assets/dsar-sla.ts)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

md
- Rotas Next.js + Better Auth + React Native: [`assets/endpoints.md`](assets/endpoints.md)