obsidian-bases
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [NO_CODE]: The skill does not include any executable scripts, binaries, or shell commands. It consists exclusively of markdown instructions and reference guides for configuring YAML files.- [PROMPT_INJECTION]: No prompt injection, jailbreak attempts, or safety bypass instructions are present. The documentation is strictly technical and focuses on the correct application of a domain-specific language (DSL). Analysis for indirect prompt injection surface:
- Ingestion points: The skill processes note frontmatter (file.properties) and metadata as data sources for views.
- Boundary markers: Data is structured via a predefined YAML schema.
- Capability inventory: Includes local file metadata access and rendering via a custom function set.
- Sanitization: Documentation provides an escapeHTML function for handling potentially unsafe strings within formulas.- [DATA_EXFILTRATION]: No network access, remote connections, or data transmission tools are defined. All operations are restricted to the local file system within the user's Obsidian vault.- [REMOTE_CODE_EXECUTION]: The skill does not perform remote code execution or download external code. It uses a restricted expression language for calculating metadata values.
Audit Metadata