gws-calendar

Pass

Audited by Gen Agent Trust Hub on May 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is configured to execute the gws binary to perform Google Calendar operations. This is the intended and documented behavior of the skill for productivity tasks.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it retrieves and processes user-controlled data from Google Calendar (such as event descriptions and titles) which could contain hidden instructions for the agent.
  • Ingestion points: Calendar event data retrieved via events.get and events.list methods in SKILL.md.
  • Boundary markers: Not present in the provided documentation.
  • Capability inventory: Command execution via the gws binary as defined in the metadata and command usage sections of SKILL.md.
  • Sanitization: No explicit sanitization or filtering of retrieved event content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
May 26, 2026, 10:52 AM
Security Audit — agent-trust-hub — gws-calendar