managing-google-meet

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to Google API domains (googleapis.com) to retrieve calendar events, meeting space configurations, and user profile information. These interactions are directed to well-known, trusted services and are essential for the skill's functionality.
  • [COMMAND_EXECUTION]: The skill utilizes standard system utilities such as curl, jq, date, and column within bash scripts to interact with APIs and format the output. The commands are structured and do not involve arbitrary or dangerous execution patterns.
  • [DATA_EXFILTRATION]: The skill accesses a sensitive environment variable ($GOOGLE_TOKEN) to authenticate with Google services. This is a standard integration pattern for agent connections. All data retrieved is sent only to official Google endpoints or displayed to the user as part of the requested meeting analysis.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, specifically Google Calendar event summaries and details. While this represents an attack surface, the skill does not utilize this data to drive sensitive capabilities like file system modifications or dynamic code execution, maintaining a safe posture.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 02:32 AM