Security audit
Security checks for vulnerabilities and agentic risk
The skill is a small typed-schema guidance package with no evidence of hidden execution, persistence, credential use, or data exfiltration.
Before installing, confirm you are comfortable with a Portuguese-oriented schema package and with the fact that the documentation overstates included modules. Review the phone-number-like example in the privacy section if sanitization matters to your use case.
The invocation description, "Use when building typed AI judgments," is broad and does not define concrete trigger conditions, exclusions, or scope boundaries. In an agent ecosystem, vague activation criteria can cause the skill to be invoked in unintended contexts, increasing the chance that sensitive decisions or workflows are routed through the wrong logic.
Most of the skill body is written in Portuguese without any indication that language selection depends on user preference. In multilingual agent systems, forcing a language can cause user confusion, misinterpretation of safety constraints, or incorrect downstream handling if the caller expects another language.
The Pydantic field descriptions are written exclusively in Portuguese, including required values like "alta", "media", and "baixa", which implies a fixed language/locale for interactions or structured outputs. The file does not indicate that users can choose their language or that this locale restriction is justified as region-specific.
No suspicious patterns detected.
