vault
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to initialize a vault structure, including creating directories under '$HOME/Documents/Obsidian/MiVault/' and generating index files.
- [DATA_EXPOSURE]: The skill manages local data by reading and writing markdown files in a user-defined vault directory and a rule graduation path ('.claude/rules/learned/').
- [INDIRECT_PROMPT_INJECTION]: The 'compile' action ingests raw external content (articles, papers) to generate wiki entries. While this creates an ingestion surface for untrusted data, the risk is mitigated by the skill's instructional focus on manual classification (GREEN/YELLOW/RED).
Audit Metadata