The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to download the @useclawlink/cli package from the NPM registry to facilitate the Google Drive integration.
[COMMAND_EXECUTION]: The skill executes shell commands via the vendor CLI to perform actions such as searching, reading, and updating Google Drive data.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Google Drive which could contain malicious instructions targeted at the agent.
Ingestion points: Data retrieved via tools like googledrive_list_comments, googledrive_download_file, and googledrive_get_file_metadata as described in SKILL.md.
Boundary markers: The skill instructions do not specify any delimiters or warnings to ignore instructions embedded in the retrieved content.
Capability inventory: The agent has the capability to execute shell commands via npx and perform write/delete operations in Google Drive.
Sanitization: There is no evidence of content filtering or sanitization being applied to the data fetched from Google Drive.

google-drive