obsidian-wiki-maintain

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (llm_wiki.py and obsidian_wiki_doctor.py) to manage Obsidian vault configuration and apply maintenance repairs. The script paths are resolved relative to the skill's installation directory.
  • [EXTERNAL_DOWNLOADS]: Includes a recommendation to install the author's verified skill package (huajiexiewenfeng/obsidian-llm-wiki) via the platform's standard command if runtime dependencies are missing.
  • [PROMPT_INJECTION]: The skill processes user-authored markdown content from Obsidian vaults, presenting a surface for indirect prompt injection.
  • Ingestion points: Reads markdown files, index.md, and log.md within the user-resolved Obsidian vault root.
  • Boundary markers: No explicit delimitation or instruction-ignoring warnings are defined for vault content ingestion.
  • Capability inventory: Invokes Python subprocesses (llm_wiki.py) and performs file-write operations to update the wiki index and logs.
  • Sanitization: Implements safety policies in references/safety-rules.md that prohibit printing discovered secrets and require preservation of author content unless explicitly asked otherwise.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 02:51 AM
Security Audit — agent-trust-hub — obsidian-wiki-maintain