obsidian-vault
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard shell commands including
findandgrepto locate files and search content within the local path/mnt/d/Obsidian Vault/AI Research/. These operations are consistent with the skill's primary purpose of note management. - [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface by reading user-controlled notes from the Obsidian vault, which could contain instructions that influence the agent's behavior.
- Ingestion points: Note content is read via
grepas described in theSKILL.mdworkflows. - Boundary markers: No delimiters or explicit instructions to ignore embedded content are provided.
- Capability inventory: Shell command execution (
find,grep) and file creation capabilities. - Sanitization: The skill does not perform any escaping or validation of the data retrieved from the Markdown files.
Audit Metadata