gog
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the external gog command-line utility via Homebrew from the steipete/tap/gogcli repository.
- [COMMAND_EXECUTION]: All Google Workspace interactions are performed by executing the gog binary with various subcommands.
- [DATA_EXFILTRATION]: The skill reads sensitive authentication material from /home/.z/google-oauth/client_secret.json to authenticate with Google APIs.
- [PROMPT_INJECTION]: The skill processes untrusted external data, posing an indirect prompt injection risk. * Ingestion points: Content is retrieved from Gmail search results, Google Drive files, Google Docs, and spreadsheet values. * Boundary markers: There are no instructions defining delimiters or warning the agent to ignore instructions embedded in the external content. * Capability inventory: The skill has the ability to send emails, create or update calendar events, and modify spreadsheet data. * Sanitization: The instructions do not specify any sanitization, filtering, or validation of the retrieved data before it enters the agent's context.
Audit Metadata