Back to skill

Security audit

Memoria Persistente

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Portuguese persistent-memory skill with no executable payload, but users should understand it is meant to keep selected memories across sessions.

Install only if you want an agent to keep selected memories across sessions. Do not save passwords, tokens, private documents, or sensitive personal details unless you have a clear way to inspect and delete the stored memory files.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description explicitly says 'Tudo em português,' which indicates the skill is intended to operate only in Portuguese. The file does not offer a user opt-in or language choice, and it does not clearly justify a strict locale limitation beyond targeting the Brazilian community. This creates a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly promotes persistent storage of user-related memories across sessions, including preferences and knowledge, but provides no privacy notice, consent mechanism, retention policy, or guidance on handling sensitive data. This creates a real risk of collecting and retaining personal or sensitive information longer than users expect, which can lead to privacy harm, unauthorized profiling, or noncompliance with data protection requirements.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The manifest text says the skill is 'essencial para desenvolvedores brasileiros' and includes locale-specific tags like 'portugues' and 'brasil'. This natural-language framing suggests a language/locale restriction or preference, but the file does not explicitly present it as an opt-in choice or document a required region-specific compliance reason.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.