obsidian-research-log
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied research and meeting logs to update local documentation. * Ingestion points: User conversations about project progress and plans. * Boundary markers: Absent; instructions are derived directly from user input. * Capability inventory: Updating local Markdown files in the Obsidian vault and .claude directory. * Sanitization: Absent; content is routed into canonical notes based on workflow rules.
- [NO_CODE]: The skill consists exclusively of instructional prompts and does not contain any executable scripts or binary files.
Audit Metadata