skills/wmy2981/skills/calendar-api/Gen Agent Trust Hub

calendar-api

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/getzdday.py executes subprocess.run("chcp 65001", shell=True) when running on Windows. This is a standard operation used to set the active code page to UTF-8 for proper character display and does not pose a security risk in this context.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of python-dotenv and tzdata via pip. These are standard, reputable libraries used for managing environment variables and timezone information.
  • [DATA_EXFILTRATION]: The script scripts/getzdday.py sends user-configured API credentials (JKHZ_ID and JKHZ_KEY) to the external domain cn.apihz.cn. This is the documented and intended behavior for interacting with the 接口盒子 API, but it involves sending sensitive keys to a third-party service.
  • [SAFE]: The skill ingests untrusted data from an external API (apihz.cn) and displays it to the user.
  • Ingestion points: API response data processed in scripts/getzdday.py.
  • Boundary markers: Absent.
  • Capability inventory: Subprocess execution for encoding and network requests for API interaction in scripts/getzdday.py.
  • Sanitization: Performs minor character replacement for formatting (| to ) but does not sanitize for potential instructions or markdown injection.
  • [SAFE]: The skill follows security best practices by recommending that API credentials be stored in .env files outside of the skill's source code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 02:07 AM
Security Audit — agent-trust-hub — calendar-api