gws-calendar
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes calendar data that can be populated by external parties.
- Ingestion points: Calendar event metadata, titles, and descriptions retrieved via methods such as events.list, events.get, and instances (SKILL.md).
- Boundary markers: The documentation refers to a shared security and auth skill (../gws-shared/SKILL.md) but does not define explicit delimiters within this file's context.
- Capability inventory: The skill enables shell command execution via the gws binary for modifying events and Access Control Lists (SKILL.md).
- Sanitization: There is no evidence of content sanitization or validation for the event data processed by the agent.
- [COMMAND_EXECUTION]: The skill operates by executing the gws command-line tool for all calendar operations, which is the intended functionality.
Audit Metadata