The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructions create a potential surface for indirect prompt injection by processing external data to drive its logic.
Ingestion points: The skill reads instructions from blueprint/20-entrevista.md and existing session state from .wca-estado.json.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard potentially malicious commands embedded within the processed files.
Capability inventory: The skill performs local file read and write operations on specific state files. It does not utilize network access or execute arbitrary shell commands.
Sanitization: No sanitization or validation of the content read from external files is specified before the agent processes the information.

configurar