obsidian-vault
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an Obsidian vault, creating a surface for indirect prompt injection.\n
- Ingestion points: Reads content and filenames from Markdown files (SKILL.md) located in the path specified by the
$OBSIDIAN_VAULTenvironment variable.\n - Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the notes are provided in the skill instructions.\n
- Capability inventory: The skill uses shell commands like
findandgrepto search and retrieve file data. It also includes workflows for creating and organizing notes, involving file-write operations (SKILL.md).\n - Sanitization: No sanitization or validation of the content read from the vault is specified.\n- [COMMAND_EXECUTION]: The skill provides specific bash command templates (e.g.,
find,grep) for the agent to execute to search and manage the local file system. These commands depend on the user-defined$OBSIDIAN_VAULTenvironment variable.
Audit Metadata