doc-obsidian

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation instructs the user to install external CLI tools: @anthropic/qmd via npm and notesmd-cli via Homebrew. @anthropic is a trusted organization, and notesmd-cli is a standard utility for markdown management.
  • [COMMAND_EXECUTION]: The skill makes extensive use of CLI tools (qmd, notesmd-cli) and shell commands (e.g., cp, date, awk, sort, sed) to manage vault files and process metadata. It includes complex shell pipelines for advanced listing and automation scripts for memory capture.
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of external data from an Obsidian vault into an AI agent's context window, which creates a surface for indirect prompt injection.
  • Ingestion points: Markdown files within the Obsidian vault retrieved using qmd search --md and notesmd-cli print.
  • Boundary markers: The skill does not provide instructions for the agent to use boundary markers or delimiters when reading vault content into its context.
  • Capability inventory: The skill allows the agent to search, read, write, move, and delete files within the local vault using the provided CLI tools.
  • Sanitization: No sanitization or content validation is specified for the note data before it is injected as LLM context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 09:35 PM