obsidian-daily
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, specifically the user's Obsidian vault, which could contain instructions intended to influence agent behavior. * Ingestion points: The obsidian daily:read, obsidian read, and obsidian search commands in SKILL.md are used to retrieve file content. * Boundary markers: The skill does not implement delimiters or explicit instructions to ignore embedded prompts within the vault data. * Capability inventory: The skill utilizes the obsidian command-line utility to read, write, and search the local file system. * Sanitization: No sanitization or filtering is applied to the content retrieved from the vault.
- [COMMAND_EXECUTION]: The skill makes use of local shell commands, specifically the obsidian CLI and the date utility, to perform its functions.
Audit Metadata