workspaces

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external application state, specifically recently opened files and workspace layouts, which represents a potential attack surface for indirect prompt injection.
  • Ingestion points: Data enters the agent context through the obsidian recents and obsidian workspace commands.
  • Boundary markers: The skill does not implement specific delimiters or warnings to ignore instructions embedded within the metadata returned by these commands.
  • Capability inventory: The skill is restricted to UI-level interactions via the obsidian CLI tool, including opening files (tab:open) and switching layouts (workspace:load).
  • Sanitization: No explicit sanitization or filtering of the output from the Obsidian CLI is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 04:07 PM
Security Audit — agent-trust-hub — workspaces