cli-anything-siyuan

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to retrieve and search through note content using commands like doc get, block get, search, and sql. If the knowledge base contains data from untrusted sources, it could include instructions designed to influence the agent's logic or behavior.
  • Ingestion points: Content returned from commands such as doc get, block get, search, and sql in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or warnings to separate note content from agent instructions.
  • Capability inventory: The skill allows for comprehensive management of notebooks, documents, and blocks, including creation, deletion, and searching via SQL.
  • Sanitization: No evidence of output sanitization or filtering is provided in the documentation.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the cli-anything-siyuan package via pip. This package facilitates the CLI operations described in the documentation and is consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 12:01 PM