The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes an external "brief" which serves as the primary input for generating email content. This constitutes an indirect prompt injection surface as the brief contains untrusted data that could potentially include instructions aimed at bypassing the agent's constraints.
Ingestion points: Untrusted data enters the context via the brief defined in SKILL.md and referenced in REFERENCIA.md.
Boundary markers: Explicit boundary markers for the brief content are not defined in the analyzed files, though the skill refers to a shared framework for artifact handling.
Capability inventory: The skill is limited to reading local context files and writing Markdown artifacts to specific project directories.
Sanitization: The skill incorporates mandatory validation through inboundfy-copy-editor and inboundfy-validador-email before concluding the task, providing a layer of oversight on the generated output.
[SAFE]: The skill operates entirely on local files and does not perform network operations, execute remote code, or request elevated privileges. It uses a clear, idempotent logic for processing content based on a predefined framework.

inboundfy-especialista-email