The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data by reading content from Google Documents, which can contain untrusted instructions.
Ingestion points: Document content retrieved via gws docs documents get as defined in SKILL.md.
Boundary markers: No explicit delimiting or instruction-ignoring markers are defined in this instruction file.
Capability inventory: The skill has document modification capabilities through the batchUpdate and create methods.
Sanitization: There are no documented sanitization or validation steps for the content retrieved from documents.
[COMMAND_EXECUTION]: The skill utilizes the gws command-line interface to perform document operations. This is a legitimate use of the tool intended for Google Workspace integration as specified in the metadata.

gws-docs