gogcli-ops
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the
Bashtool to run thegogCLI utility for interacting with Google Drive, Sheets, Docs, and Slides.\n- [COMMAND_EXECUTION]: Runs a local Python scriptscripts/gog_parse_url.pyto extract file IDs from provided URLs or text.\n- [PROMPT_INJECTION]: Vulnerable to indirect prompt injection through the processing of untrusted data from external Google Workspace documents.\n - Ingestion points: Reads file content using
gog docs catand spreadsheet data viagog sheets get(as referenced in SKILL.md).\n - Boundary markers: Does not define delimiters or specific instructions to ignore embedded commands within the retrieved data.\n
- Capability inventory: The agent is equipped with the
Bashtool (defined in SKILL.md), providing a high-impact execution environment for any instructions found in the data.\n - Sanitization: The skill does not implement sanitization or validation logic for the content fetched from the Google API.
Audit Metadata