obsidian-markdown
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and syntax references for Obsidian note-taking. It does not include any scripts, shell command executions, or external software dependencies.
- [PROMPT_INJECTION]: No attempts to override system prompts, bypass safety filters, or use adversarial role-play patterns were detected.
- [DATA_EXFILTRATION]: The skill does not contain logic to access sensitive local files (e.g., .ssh, .env) or perform outbound network requests.
- [REMOTE_CODE_EXECUTION]: The skill does not perform remote script downloads or execute code from external sources. Links provided in the references target the official Obsidian help site, which is a well-known service.
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for processing markdown data. 1. Ingestion points: Obsidian .md files as described in the frontmatter. 2. Boundary markers: Not specified. 3. Capability inventory: No tools or executable functions are defined in the skill files. 4. Sanitization: Not specified. As the skill provides no active capabilities, the risk of indirect injection is negligible.
Audit Metadata