goog
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill operates entirely through shell command execution using the
googCLI utility. It also supports development workflows usingcargo runandtarget/debug/goog. - [PROMPT_INJECTION]: The skill processes untrusted external data from Gmail, Google Drive, and Google Docs, which creates an indirect prompt injection surface.
- Ingestion points: Untrusted content enters the agent's context through tools like
goog mail read,goog docs get, andgoog drive download(documented in references/docs.md and references/drive.md). - Boundary markers: The instructions do not explicitly require the use of delimiters or 'ignore' instructions for the data being processed.
- Capability inventory: The skill possesses extensive capabilities including file system writes (downloads), network operations (via the CLI), email drafting, and calendar modifications.
- Sanitization: There are no instructions for sanitizing or validating external input before it is processed by the agent.
Audit Metadata