The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing external interaction data.
Ingestion points: The skill ingests daily interaction episodes provided by the episodic-archiver and other persona sources to generate journal content.
Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the analyzed configuration or wrapper scripts.
Capability inventory: The skill is granted Bash, Read, and Write permissions. It executes Python modules and shell scripts capable of system interaction.
Sanitization: No sanitization or filtering logic for the input interaction data is present in the provided skill files.

create-journal-entry