google-calendar

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires several standard Python libraries for Google API interaction and security, including google-auth, google-api-python-client, and keyring.
  • [DATA_EXFILTRATION]: Network communication is restricted to official Google API domains (googleapis.com). Sensitive authentication tokens are stored using the system keyring service rather than plain text configuration files.
  • [COMMAND_EXECUTION]: The skill uses a local Python script to interface with the Google Calendar API and manage user configuration.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection from malicious instructions embedded in calendar events.
  • Ingestion points: Calendar event summaries and descriptions are retrieved via the API in scripts/google-calendar.py.
  • Boundary markers: No explicit delimiters or instructions are used to separate untrusted event data from system instructions.
  • Capability inventory: The agent has the ability to create, update, and delete calendar events.
  • Sanitization: No sanitization or filtering is performed on the content retrieved from the Google Calendar API.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 06:40 PM