The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data, such as editorial bases and external 'acervo' files, which provides a surface for indirect instructions to influence agent behavior.
Ingestion points: The skill reads multiple configuration and content files from the .inboundfy/ and acervo/ directories (e.g., SKILL.md, REFERENCIA.md).
Boundary markers: There are no explicit instructions to use delimiters or ignore potentially malicious directives embedded within the processed marketing content.
Capability inventory: The skill is capable of executing CLI tools (inboundfy) and writing files to the local repository (canais/ directory).
Sanitization: The instructions do not specify any sanitization or validation logic for the content being processed.
[COMMAND_EXECUTION]: The skill uses localized command-line utilities to automate the production and validation of marketing assets.
Evidence: The workflow involves executing commands such as inboundfy content create, inboundfy-setup, and inboundfy-anti-slop to perform setup, content generation, and quality audits.

inboundfy-producao