gws-workflow-email-to-task

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious instructions, obfuscation, or unauthorized data access patterns were detected.
  • [COMMAND_EXECUTION]: The skill documents the use of the 'gws' command-line tool. This usage is transparent and consistent with the skill's stated purpose of providing Google Workspace automation.
  • [PROMPT_INJECTION]: The skill does not contain any instructions that attempt to override agent behavior or bypass safety guardrails.
  • [DATA_EXPOSURE]: The skill processes Gmail data for conversion to tasks but specifies that the agent should confirm with the user before execution, serving as a safety checkpoint.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 01:27 PM
Security Audit — agent-trust-hub — gws-workflow-email-to-task