skills/g1joshi/agent-skills/obsidian/Gen Agent Trust Hub

obsidian

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of local Markdown files (vault notes), which can contain untrusted instructions if content is sourced from external actors or web clippings.
  • Ingestion points: Markdown notes stored in the local Obsidian vault (referenced throughout SKILL.md).
  • Boundary markers: No boundary markers, delimiters, or instructions to ignore embedded commands are suggested for the data processing workflows.
  • Capability inventory: The skill provides functional templates for shell command execution (Git CLI sync scripts) and JavaScript execution (DataviewJS query blocks).
  • Sanitization: The provided script and query examples do not include any sanitization or validation of the note content before execution or processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 03:37 AM