vault
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
joelclawCLI to perform read and search operations on an Obsidian vault. This is a vendor-owned resource used for the skill's intended purpose. - [PROMPT_INJECTION]: The skill ingests and processes content from markdown files within the vault, which could potentially contain indirect prompt instructions.
- Ingestion points: Content is retrieved via
joelclaw vault readandjoelclaw vault searchcommands. - Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided.
- Capability inventory: The skill is designed for reading files, searching content, and performing directory listings.
- Sanitization: The skill does not describe specific sanitization or validation of the content read from the vault files.
Audit Metadata