gws-workflow-weekly-digest

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires and executes the gws command-line tool, which is a vendor-provided binary used to fetch workspace data.
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
  • Ingestion points: The skill processes untrusted data from external sources, specifically Gmail (unread emails) and Google Calendar (meeting details), to create a digest.
  • Boundary markers: There are no explicit delimiters or instructions provided in this file to prevent the agent from obeying instructions hidden within emails or calendar events.
  • Capability inventory: The skill executes the gws binary for data retrieval. No file-write or direct network operations are defined in the analyzed file.
  • Sanitization: No evidence of sanitization or content filtering is present in the skill's markdown instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 10:49 PM