soia-pkm-bootstrap-vault-base

Warn

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes an optional dependency on the huashu-weread-advisor tool, which is installed from a repository belonging to a third-party developer (alchaincyf/huashu-weread).
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download the weread-skills tool from a well-known service's repository (Tencent/WeChatReading).
  • [COMMAND_EXECUTION]: The skill executes a Python script (scripts/init_vault.py) to scaffold a knowledge base by creating directories and writing Markdown files locally.
  • Ingestion points: scripts/init_vault.py reads configuration data from user-provided JSON or YAML files through the --config CLI argument.
  • Boundary markers: The content of files created by the script is taken directly from the configuration file without specific delimiters or instructions to ignore embedded content.
  • Capability inventory: scripts/init_vault.py performs file system operations including directory creation (mkdir) and file writing (write_text).
  • Sanitization: Target paths are processed using .expanduser().resolve() to normalize directory locations before file operations are performed.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 16, 2026, 08:22 AM
Security Audit — agent-trust-hub — soia-pkm-bootstrap-vault-base