wiki-dashboard

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's operations are confined to the local file system for the purpose of vault management. No malicious patterns, obfuscation, or remote code execution were identified.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes content from the user's Obsidian vault to inform its dashboard creation logic.
  • Ingestion points: The agent reads the vault's index file at '$OBSIDIAN_VAULT_PATH/index.md' and inspects the frontmatter of notes across the vault.
  • Boundary markers: There are no explicit delimiters or specific instructions to the agent to disregard potential instructions embedded within the vault files being read.
  • Capability inventory: The skill enables the agent to write new YAML files ('.base' files) to the '_meta/' directory and modify existing markdown notes to embed these dashboards.
  • Sanitization: The skill does not describe any specific sanitization or validation steps for the content ingested from the vault files before using that data to build queries.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 03:34 PM