pp-google-calendar

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs its core binary, google-calendar-pp-cli, from the author's official NPM package (@mvanhorn/printing-press-library) and GitHub repository (github.com/mvanhorn/printing-press-library). These are vendor-controlled resources.
  • [COMMAND_EXECUTION]: The skill relies on the Bash tool to execute the google-calendar-pp-cli binary and manage the installation process via npx and go install.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Google Calendar event fields, which could serve as a vector for indirect prompt injection.
  • Ingestion points: Event summaries, descriptions, and metadata retrieved via agenda, events list, and events get subcommands.
  • Boundary markers: Absent. The instructions do not define delimiters or isolation prompts for external calendar content.
  • Capability inventory: The skill has the ability to write to the file system using --deliver file:, perform network POST requests via --deliver webhook:, and execute shell commands through the Bash tool.
  • Sanitization: Absent. The skill does not mention escaping or validating event strings before they are processed by the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 09:01 AM
Security Audit — agent-trust-hub — pp-google-calendar