zettelkasten

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-authored Markdown notes which creates a surface for indirect prompt injection.
  • Ingestion points: Notes are read from the ~/Documents/xiaodazi/zettelkasten/ directory (File: SKILL.md).
  • Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions embedded in the note content.
  • Capability inventory: The skill utilizes shell-based search (grep) and file system operations to interact with and process the notes.
  • Sanitization: No sanitization or validation of the note content is described before the agent processes or searches the files.
  • [COMMAND_EXECUTION]: Executes shell commands such as grep to search and retrieve content from the local zettelkasten files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 04:20 PM