obsidian-vault-context
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads markdown files from the Obsidian vault, creating a surface for indirect prompt injection where malicious content in a note could influence agent behavior.\n
- Ingestion points: The skill reads files from the
$VAULT_PATH/Daily/folder and other research directories as described in the 'Common Operations' section ofSKILL.md.\n - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands when reading vault files.\n
- Capability inventory: The skill uses file write/edit tools and executes shell commands via the
obsidian-clitool.\n - Sanitization: No validation or sanitization of the content read from files is mentioned or required in the instructions.\n- [COMMAND_EXECUTION]: The skill instructs the agent to run the
obsidian-cliutility to determine the vault location (obsidian-cli print-default) and perform UI-related tasks like opening (obsidian-cli open) or moving notes (obsidian-cli move).
Audit Metadata