gws-calendar-insert

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local binary named gws to interact with Google Calendar. It uses command-line flags to pass user-specified data such as event titles and descriptions.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted user input (e.g., event summaries or descriptions) that is then passed to the gws tool.
  • Ingestion points: Flags --summary, --location, and --description in SKILL.md.
  • Boundary markers: None provided in the command examples.
  • Capability inventory: Execution of the gws CLI tool.
  • Sanitization: No explicit sanitization or escaping logic is defined within the skill file, but the skill includes a specific caution note instructing the agent to confirm with the user before performing write operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 01:27 PM
Security Audit — agent-trust-hub — gws-calendar-insert