skills/aaaaqwq/agi-super-skills/gog/Gen Agent Trust Hub

gog

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill operates by executing the gog binary on the local system to interact with various Google Workspace APIs.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of a third-party binary via the steipete/tap/gogcli Homebrew tap.
  • [PROMPT_INJECTION]: The skill processes data from external sources such as Gmail messages, Google Docs, and Google Sheets, which creates an indirect prompt injection surface.
  • Ingestion points: gog gmail search, gog sheets get, and gog docs cat commands in SKILL.md fetch external data.
  • Boundary markers: No markers or explicit instructions to ignore embedded commands are present in the skill's instructions.
  • Capability inventory: The skill has the ability to send emails (gog gmail send) and update spreadsheet data (gog sheets update) as seen in SKILL.md.
  • Sanitization: No content validation or sanitization of the fetched data is mentioned or implemented before it reaches the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:14 PM