The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from various external sources, including user transcripts, WhatsApp messages, field notes, and content from external URLs provided as fichero_input. This data is directly integrated into the agent's context for ideation and subsequently written to persistent storage.
Ingestion points: Processes external raw content via fichero_input (URL, text, or attachments) and user-provided notes from communication platforms (WhatsApp, transcripts).
Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to ignore embedded commands within the processed data.
Capability inventory: Includes file-writing and state-management capabilities such as criar_ficha, guardar_ficha, and transition_ficha, alongside updates to the wachines-brain repository.
Sanitization: There is no evidence of input validation, escaping, or sanitization before the external content is processed or saved back to the system.

wachi-ideacion