obsidian
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to read and process arbitrary Markdown files from an Obsidian vault, which serves as an ingestion point for untrusted data.
- Ingestion points: Note content is accessed through
obsidian read,sed, andrgcommands as specified inSKILL.md. - Boundary markers: The instructions do not define clear delimiters or specific instructions for the agent to ignore or isolate potentially malicious commands embedded within the notes.
- Capability inventory: The skill possesses write and move capabilities (
obsidian create,obsidian move,apply_patch), which could be abused if an injection succeeds. - Sanitization: No sanitization logic is provided to filter or validate the contents of the vault files before they are interpreted by the agent.
- [COMMAND_EXECUTION]: The skill frequently invokes shell commands and a local CLI tool to interact with the filesystem and application configuration.
Audit Metadata