dingtalk-calendar

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes Python scripts to wrap and automate calls to the local dws CLI utility.
  • Evidence: The function run_dws in scripts/calendar_free_slot_finder.py, scripts/calendar_schedule_meeting.py, and scripts/calendar_today_agenda.py uses subprocess.run(['dws'] + args, ...).
  • Analysis: The implementation uses list-based command execution with shell=False (the default), which is a secure pattern that prevents command injection from untrusted input.
  • [SAFE]: Analysis of the scripts and instructions reveals no patterns of data exfiltration, persistence, or malicious behavior.
  • The skill focuses on its primary purpose of interacting with the DingTalk calendar ecosystem via an authorized binary.
  • All network activity is handled through the existing dws tool, and no sensitive file access or credential harvesting was detected.
  • [SAFE]: Potential indirect prompt injection surfaces are limited by the specialized nature of the tool.
  • Ingestion Points: The skill reads calendar event data via dws calendar event list.
  • Capability Inventory: Actions are restricted to calendar and meeting room management via the dws binary.
  • Sanitization: The scripts parse JSON output from the binary and format it for display, minimizing the risk of unintended instruction execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 11:21 AM
Security Audit — agent-trust-hub — dingtalk-calendar