The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to utilize grep -ril for locating specific files within the local filesystem (specifically ~/Obsidian/). While restricted to the user's home directory, this pattern involves direct interaction with the shell to perform factual lookups based on user-provided queries.
[PROMPT_INJECTION]: Indirect Prompt Injection surface detected. The skill processes external data (clipped sources, learnings, and references) stored in the ~/Obsidian/Library/ directory and synthesizes answers from them. Maliciously crafted content within these files could potentially influence agent behavior.
Ingestion points: Local markdown files and indexes located in ~/Obsidian/ subdirectories.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
Capability inventory: The skill uses grep for discovery and Read for content extraction.
Sanitization: There is no evidence of content sanitization or validation before the synthesis and citation phase.

ask