gws-workflow-weekly-digest

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the 'gws' command-line tool to aggregate calendar events and email counts. This is a standard execution pattern for CLI-based productivity skills.
  • [PROMPT_INJECTION]: The skill processes data from Gmail and Google Calendar, which constitutes an indirect prompt injection attack surface. Evidence Chain: 1. Ingestion points: Meeting details and email summaries retrieved via 'gws' CLI. 2. Boundary markers: None explicitly defined in the prompt instructions to isolate untrusted content. 3. Capability inventory: No dangerous capabilities (e.g., filesystem writes, network exfiltration, or arbitrary code execution) are present in the skill. 4. Sanitization: No data sanitization or filtering logic is provided in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 01:27 PM
Security Audit — agent-trust-hub — gws-workflow-weekly-digest