recipe-review-overdue-tasks

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: Analysis of the skill's instructions confirms they are limited to legitimate task management operations. No obfuscation, data exfiltration, or safety bypasses were detected.
  • [COMMAND_EXECUTION]: The skill uses the gws binary to list task lists and tasks. This is standard behavior for the intended functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from Google Tasks. While these are external inputs, the skill's focus on metadata (due dates) and the lack of complex data processing minimize the risk of indirect injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 04:56 PM