cli-anything-siyuan

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends the installation of the cli-anything-siyuan Python package, which is a tool provided by the author to interface with the SiYuan application.\n- [COMMAND_EXECUTION]: The skill uses various shell commands to manage notes and notebooks, including executing SQL queries on a local block database.\n- [PROMPT_INJECTION]: The skill presents an ingestion surface for indirect instructions by reading content from the local SiYuan knowledge base.\n
  • Ingestion points: Note content retrieved through search, block get, and sql commands.\n
  • Boundary markers: The skill does not define specific delimiters for external content.\n
  • Capability inventory: The agent can execute shell commands through the cli-anything-siyuan utility.\n
  • Sanitization: No sanitization of the retrieved content is specified in the skill instructions.\n- [SAFE]: No malicious patterns, data exfiltration, or unauthorized access behaviors were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 12:09 AM
Security Audit — agent-trust-hub — cli-anything-siyuan