The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external email messages, which could contain instructions aimed at overriding agent behavior.
Ingestion points: The skill uses read_message and search_messages to fetch external email content from Gmail (SKILL.md).
Boundary markers: There are no explicit instructions for using delimiters or boundary markers to isolate email content from agent instructions.
Capability inventory: The skill possesses write capabilities including send_message, archive, and modify_labels (SKILL.md).
Sanitization: The instructions do not specify any sanitization or validation steps for content retrieved from messages before it is processed or used in further actions.

gmail