cli-anything-obsidian
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to install the
cli-anything-obsidianpackage via the Python Package Index (PyPI). - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from an Obsidian vault, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: External data enters the agent context through
vault read,search simple, andsearch querycommands defined inSKILL.md. - Boundary markers: The instructions do not implement boundary markers or instructions to ignore commands embedded within the retrieved note content.
- Capability inventory: The skill permits modification of the vault (
vault create,vault update,vault append) and execution of Obsidian application commands (command execute), which could be triggered by malicious content in a note. - Sanitization: There is no evidence of content sanitization, validation, or filtering for data retrieved from the vault.
Audit Metadata