The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes several spark CLI commands (spark events, spark emails, spark team, spark meetings) to retrieve information for the weekly digest. These operations are consistent with the skill's stated purpose of summarizing user data.
[SAFE]: The skill presents an indirect prompt injection surface by ingesting and summarizing external data from email bodies and meeting transcripts.
Ingestion points: spark emails and spark meetings commands (found in SKILL.md).
Boundary markers: None explicitly used to wrap retrieved content.
Capability inventory: The skill is limited to reading data; it contains no file-write, network transmission, or code execution capabilities.
Sanitization: No explicit sanitization or filtering is performed on the content before summarization.

spark-recipe-weekly-digest