The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard Unix shell utilities including find, ls, grep, wc, sort, and uniq to visualize folder structures, count files, and search for specific markdown notes.
[PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by reading content from user-controlled markdown files.
Ingestion points: Markdown files located within the user-defined ${VAULT_PATH} as described in the navigation patterns in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when reading note content.
Capability inventory: The agent can perform file system searches (find, ls), search file contents (grep), and read full file contents using a Read tool.
Sanitization: There is no evidence of sanitization, filtering, or validation of the content found within the markdown notes before the agent processes them.

obsidian-vault