obsidian-vault-builder
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides templates and instructions for executing shell commands via an external CLI tool and custom JavaScript macros. Evidence: references/interaction-patterns.md lists various obsidian.com subcommands for index-aware vault operations; references/voice-capture-macro.md contains a script (transcribeVoice.js) that uses child_process.execFile to run the claude binary.
- [DYNAMIC_EXECUTION]: The skill includes JavaScript code snippets intended to be used as QuickAdd User Scripts within the Obsidian environment. Evidence: references/voice-capture-macro.md contains pickVoiceFile.js and transcribeVoice.js, which are executed at runtime by the QuickAdd plugin to automate vault tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from an Obsidian vault, which may contain untrusted content that could influence the agent's behavior. Ingestion points: SKILL.md and references/interaction-patterns.md describe reading vault files directly via the filesystem and indexing content via CLI tools. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified for the vault content processing. Capability inventory: The skill utilizes file write/edit operations, network requests via curl, and shell command execution (obsidian.com, execFile). Sanitization: No evidence of input sanitization or filtering for the processed vault data was found.
Audit Metadata