skills/craftos-dev/craftbot/gog/Gen Agent Trust Hub

gog

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the gog CLI via a Homebrew tap (steipete/tap/gogcli) to enable Workspace integration.
  • [COMMAND_EXECUTION]: The agent executes the gog CLI to manage Gmail, Calendar, Drive, and Sheets, which involve running shell commands with user-controlled parameters.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the handling of external data from Google services.
  • Ingestion points: External data is ingested through Gmail search results, Drive file content, and Sheets data retrieved via gog commands (e.g., gog gmail search, gog docs cat).
  • Boundary markers: No specific delimiters or safety instructions are used to isolate external content from the agent's core instructions.
  • Capability inventory: The agent can perform high-impact actions like sending emails (gog gmail send) and modifying spreadsheets (gog sheets update) based on retrieved data.
  • Sanitization: There is no evidence of sanitization or validation of the retrieved content before it is processed by the language model.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 12:15 AM
Security Audit — agent-trust-hub — gog