gws-calendar
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires and uses the
gwsCLI tool to perform all operations. It provides a structured interface to call various API methods (e.g.,gws calendar events list). - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads content from external sources (Google Calendar events). An attacker could place malicious instructions in an event description that the agent might inadvertently follow when processing the data.
- Ingestion points: Event descriptions, titles, and calendar metadata retrieved via
events.list,events.get, andcalendars.get. - Boundary markers: None specified in this file; it refers to a shared file (
gws-shared/SKILL.md) for security rules. - Capability inventory: The agent has the ability to execute shell commands using the
gwsbinary to read, write, and delete calendar data. - Sanitization: The skill does not describe any specific sanitization or filtering of the retrieved event content before it is processed by the agent.
Audit Metadata