The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads and searches content from local markdown files in an Obsidian vault. This provides a surface for indirect prompt injection where malicious instructions embedded in notes could influence the agent's subsequent actions.
Ingestion points: Note content is ingested via cat and grep commands as shown in SKILL.md.
Boundary markers: Absent; note content is read directly into the agent context without delimiters or safety instructions.
Capability inventory: The skill has the ability to read, search, create, and append to files on the local filesystem using shell commands.
Sanitization: No sanitization is performed on the content of the notes before the agent processes them.
[COMMAND_EXECUTION]: The skill relies on shell command execution (cat, find, ls, grep, echo) to perform its primary functions. While these are standard tools for vault management, they operate directly on the filesystem.

obsidian