gog
Warn
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- EXTERNAL_DOWNLOADS (MEDIUM): The skill installs the
gogbinary via a third-party Homebrew tap (steipete/tap/gogcli). This repository is not on the list of trusted GitHub organizations or repositories. Users are executing code from an unverified third-party source. - COMMAND_EXECUTION (LOW): The skill provides the agent with the ability to execute the
gogcommand-line tool. This tool is granted extensive access to the user's Google account (Gmail, Calendar, Drive, Contacts, Sheets, and Docs) following OAuth authentication. - Indirect Prompt Injection (LOW):
- Ingestion points: The agent reads untrusted data via
gog gmail search,gog drive search,gog docs cat, andgog sheets get(File: SKILL.md). - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the provided skill text.
- Capability inventory: The agent has the capability to send emails (
gog gmail send), create calendar events, and modify spreadsheets. - Sanitization: No evidence of sanitization or filtering of external content before processing. This creates a risk where a malicious email or document could contain instructions that the agent mistakenly follows.
Audit Metadata