skills/lidge-jun/cli-jaw-skills/gog/Gen Agent Trust Hub

gog

Warn

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill metadata specifies the installation of a third-party command-line tool using Homebrew: brew install steipete/tap/gogcli.
  • [COMMAND_EXECUTION]: The skill provides numerous instructions for executing shell commands to interact with Gmail, Calendar, Drive, Contacts, Sheets, and Docs using the gog binary.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its ability to ingest untrusted data and perform automated actions based on that data.
  • Ingestion points: Gmail message content (gog gmail search), Google Drive file contents (gog drive search), Google Sheets data (gog sheets get), and Google Docs text (gog docs cat).
  • Boundary markers: Absent. The instructions do not include delimiters or specific system-level warnings to the agent regarding the processing of untrusted content fetched from these services.
  • Capability inventory: The skill allows for high-impact actions including sending emails (gog gmail send), replying to messages, creating or updating calendar events (gog calendar create), and modifying spreadsheet data (gog sheets update).
  • Sanitization: No sanitization, validation, or filtering of the ingested data is performed or instructed before the agent processes the content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 2, 2026, 01:52 PM