The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard shell utilities such as find, sed, cat, and echo to manage files. These operations are restricted to the user-configured VAULT_PATH and are necessary for the skill's primary purpose of template discovery and application.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from external template files which could potentially contain malicious instructions.
Ingestion points: Template content is read from the local file system using cat and find in SKILL.md.
Boundary markers: No explicit delimiters are used to wrap the ingested content to prevent the agent from interpreting it as instructions.
Capability inventory: The skill has the ability to read and write files within the user's filesystem and execute shell commands.
Sanitization: No content sanitization or instruction filtering is performed on the template data before it is displayed or processed.

obsidian-templates