obsidian-search
Warn
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses Bash to execute system commands. Evidence: SKILL.md specifies executing commands using Bash.
- [DYNAMIC_EXECUTION]: The skill constructs shell commands by interpolating user input into fixed templates like 'obsidian search query="..."'. The absence of sanitization for shell metacharacters (e.g., ;, |, `) allows for potential command injection.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from local Obsidian notes. 1. Ingestion points: 'obsidian read', 'obsidian search:context' in references/cli-query-patterns.md. 2. Boundary markers: Absent; the agent is not instructed to ignore directives within note text. 3. Capability inventory: Bash shell execution via the CLI tool. 4. Sanitization: Absent.
Audit Metadata