organizing-obsidian-vault
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill employs standard shell utilities including
find,mkdir, andcpto locate vault files and create timestamped backups before performing any modifications. - [REMOTE_CODE_EXECUTION]: The skill instructs the agent to execute a bundled Python script located at
scripts/platforms.pyto identify the Obsidian vault path based on the operating system's environment. - [PROMPT_INJECTION]: The skill acknowledges the risk of indirect prompt injection by processing markdown notes and explicitly directs the agent to ignore any command-like text within those notes.
- Ingestion points: Markdown files (.md) within the Obsidian vault (SKILL.md).
- Boundary markers: Uses specific instructional boundaries to distinguish between user data and agent instructions.
- Capability inventory: The agent possesses file system read/write capabilities and the ability to execute local scripts and shell commands.
- Sanitization: The skill relies on instructional logic rather than technical content sanitization.
Audit Metadata