The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of gws CLI commands to interact with the Google Drive API. It includes explicit security rules instructing the agent to confirm write or delete operations with the user and suggesting the use of --dry-run for destructive tasks.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes data from external sources (Google Drive files via files list, get, and export).
Ingestion points: Methods defined in SKILL.md for retrieving file metadata and content.
Boundary markers: Absent. The skill does not define specific delimiters or instructions to treat ingested file content as untrusted.
Capability inventory: The skill has the ability to write to the filesystem (-o flag), upload files, and modify permissions (permissions create), which could be targeted by instructions found in processed files.
Sanitization: Absent. There are no instructions for sanitizing or validating the content retrieved from the API.

gws-drive