obsidian-graph-traversal

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill focuses on local data processing within an Obsidian vault. It uses a Python script (scripts/graph_ops.py) to scan markdown files for wikilinks and construct an in-memory graph.
  • [COMMAND_EXECUTION]: The skill executes local Python scripts via the Bash tool. The scripts use the standard argparse library to handle user-provided inputs like vault paths and note names safely.
  • [DATA_EXPOSURE]: No data exfiltration patterns were detected. The skill reads local file content to extract metadata (links) but does not transmit this information over the network or expose sensitive system files.
  • [PROMPT_INJECTION]: The skill's instructions and script logic do not contain any patterns associated with prompt injection, safety bypasses, or role-play attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 08:12 PM