obsidian-performance-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by reading the contents of markdown files from the Obsidian vault, which could contain malicious instructions designed to influence the agent.
- Ingestion points: The skill uses
this.app.vault.cachedRead(file)inSKILL.md(Step 3) andreferences/implementation.md(EfficientFileProcessor) to read file content for processing. - Boundary markers: There are no delimiters or instructions to ignore embedded prompts when reading vault file content.
- Capability inventory: The skill environment has access to file reading, writing, and editing tools, as well as the ability to execute npm commands and manipulate the Obsidian UI.
- Sanitization: The skill lacks validation or sanitization of the file content before it is processed or used in logic.
Audit Metadata