ClawHub
Back to skill

Security audit

Autonomia Agente

Security checks for vulnerabilities and agentic risk

Overview

This is a Portuguese Markdown-only autonomy skill whose persistence and proactive-agent behavior are disclosed and aligned with its stated purpose, though users should be aware it may write interaction notes locally.

Install only if you want your agent to keep local working notes and behave more proactively. Avoid using it around sensitive conversations unless you are comfortable with those details being written under .autonomia, and periodically review or delete those files as needed.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Indirect Prompt Extraction

Medium
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md
✅ **Antecipa suas necessidades** — Pergunta "o que ajudaria meu humano?" em vez de esperar

✅ **Reverse prompting** — Surpreende com ideias que você não sabia que precisava

✅ **Check-ins proativos** — Monitora o que importa e reach out quando necessário

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

A skill anuncia WAL Protocol, Working Buffer e recuperação persistente, mas não traz aviso claro de que dados de interação serão gravados e mantidos entre sessões. Isso cria risco de retenção não transparente de informações sensíveis, surpresa do usuário e possível exposição de histórico, especialmente porque a persistência é um componente central da skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

A ativação por gatilhos amplos como 'quando quiser que seu agente seja mais proativo' ou 'memória persistente entre sessões' é vaga e favorece uso excessivo ou automático sem consentimento contextual claro. Em uma skill de autonomia, isso aumenta o risco de o agente assumir comportamentos persistentes, monitoramento e iniciativa além do esperado pelo usuário.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest text specifically targets 'desenvolvedores brasileiros' and tags the skill with 'portugues' and 'brasil', which indicates a language/locale constraint in the skill metadata. There is no indication that users can opt into another language or that the locale restriction is required for a region-specific compliance purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

A seção 'Em Português' afirma que a skill foi criada especialmente para a comunidade brasileira, mas não oferece opção explícita de idioma/locale nem esclarece se esse foco regional é apenas descritivo. Isso pode configurar restrição de idioma ou localidade sem opt-in do usuário.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.