gws-calendar
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to fetch and process calendar event data, which may contain instructions from external third parties. * Ingestion points: Content is retrieved using methods like
events.listandevents.getdefined inSKILL.md. * Boundary markers: There are no boundary markers or instructions to the agent to disregard instructions found within calendar data. * Capability inventory: The skill uses thegwsbinary to execute commands based on these resources. * Sanitization: No input sanitization or validation is applied to the calendar data before processing. - [COMMAND_EXECUTION]: The skill is designed to execute the
gwscommand-line tool to manage calendar resources, which is its primary function.
Audit Metadata