The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external project files which could contain malicious instructions designed to influence the agent's behavior during pricing analysis.
Ingestion points: Files located in .inboundfy/context/, .inboundfy/estrategia.md, and .inboundfy/fontes-projeto.md are read into the agent context.
Boundary markers: The instructions mandate following a shared contract (../_shared/02-contrato-de-artefato.md) and specific templates, but no explicit data delimiters are defined in the analyzed files.
Capability inventory: The skill reads local project files, writes or updates reports based on its analysis, and invokes other skills such as inboundfy-setup and inboundfy-anti-slop.
Sanitization: The workflow includes a revision step using inboundfy-anti-slop and inboundfy-copy-edicao to validate the generated output.

inboundfy-growth-pricing