gog
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill configuration specifies the installation of the
gogCLI tool from a third-party Homebrew tap (steipete/tap/gogcli). This introduces a dependency on an external binary maintained outside of the primary skill environment. - [COMMAND_EXECUTION]: The skill relies on executing various subcommands of the
gogtool to interact with Google Workspace APIs. This includes reading, writing, and deleting data across multiple Google services. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external sources which could be used to influence the agent's actions through embedded instructions.
- Ingestion points: Content is ingested through
gog gmail search,gog drive search,gog sheets get, andgog docs catcommands inSKILL.md. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the skill instructions.
- Capability inventory: The skill has the capability to send emails (
gog gmail send), modify spreadsheet data (gog sheets update,gog sheets append,gog sheets clear), and write files to the local system (gog docs export --out /tmp/doc.txt). - Sanitization: There is no evidence of sanitization, filtering, or validation of the data retrieved from Google Workspace before it is presented to the agent's context.
Audit Metadata