google-calendar
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npx @useclawlink/clito perform actions. This involves downloading and executing the command-line interface from the NPM registry. As this is the official tool of the skill author (clawlink-hq), it is considered a legitimate vendor resource. - [COMMAND_EXECUTION]: The skill operates by executing shell commands via the
@useclawlink/clitool to interact with the Google Calendar API. - [CREDENTIALS_UNSAFE]: The documentation specifies that credentials are stored locally at
~/.clawlink/credentials.json. This is standard practice for CLI-based authentication and does not represent a credential leak in the skill code itself. - [PROMPT_INJECTION]: The skill processes data from external sources (calendar event details) which could contain malicious instructions. The skill mitigates this risk by explicitly instructing the agent to confirm with the user before performing any write operations like creating or deleting events.
- Ingestion points: calendar data retrieved via
googlecalendar_events_listandgooglecalendar_events_get. - Boundary markers: The instructions state "confirm with the user before any write".
- Capability inventory: File system access (credentials) and shell command execution via the CLI tool.
- Sanitization: Relies on the underlying CLI and API for data handling.
Audit Metadata