skills/gen-verse/openclaw-rl/gog/Gen Agent Trust Hub

gog

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches and installs the gog command-line tool via Homebrew using the steipete/tap/gogcli formula.
  • [COMMAND_EXECUTION]: Executes the gog CLI to interact with various Google Workspace services, including Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
  • [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by processing external data at runtime.
  • Ingestion points: Retrieves content from Gmail messages, Drive files, Sheets cells, and Google Docs using commands like gog gmail search, gog docs cat, and gog sheets get (SKILL.md).
  • Boundary markers: The instructions do not define boundary markers or delimiters to separate ingested content from system instructions.
  • Capability inventory: The skill provides powerful capabilities that could be abused if an injection is successful, such as sending emails (gog gmail send), modifying spreadsheets (gog sheets update), and creating calendar events (gog calendar create).
  • Sanitization: There is no evidence of sanitization or validation of the data retrieved from Google Workspace APIs before it is passed to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 02:37 AM