gws-workflow-weekly-digest

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the gws command-line tool to retrieve data from Google Workspace. This is expected behavior for a tool authored by 'googleworkspace'.\n- [SAFE]: No signs of malicious code, obfuscation, or unauthorized data exfiltration were detected in the skill instructions.\n- [PROMPT_INJECTION]: The skill identifies a potential attack surface for indirect prompt injection as it processes untrusted data from emails and calendar events. 1. Ingestion points: Gmail (unread emails) and Calendar (meetings). 2. Boundary markers: None identified in this skill. 3. Capability inventory: gws CLI execution. 4. Sanitization: Not specified. This finding is considered safe as it is the primary intended function of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 01:46 AM