The Agent Skills Directory

[PROMPT_INJECTION]: The skill is designed to read and process content from Google Drive, which introduces a surface for indirect prompt injection if files contain malicious instructions.
Ingestion points: External content enters the agent's context through the /get-file and /find-file actions (file content and metadata).
Boundary markers: The instructions do not define delimiters or specific 'ignore' instructions for the data retrieved from Google Drive.
Capability inventory: The skill possesses write capabilities, including folder and file creation (/create-file, /create-folder).
Sanitization: There is no evidence of content sanitization or validation of the data retrieved from external files.
[COMMAND_EXECUTION]: The skill executes the orth command-line interface. These commands are directed towards the developer's official domain and represent standard functional implementation for this vendor's ecosystem.

google-drive