The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands for project operations such as building, linting, and version control.\n
Evidence: references/build-workflow.md specifies execution of npm run build and npx grunt build.\n
Evidence: references/quick-sync-guide.md and references/sync-procedure.md automate git pull and git log commands.\n- [EXTERNAL_DOWNLOADS]: The skill fetches configuration and documentation from well-known sources.\n
Evidence: references/sync-procedure.md contains workflows for pulling updates from Obsidian's official GitHub repositories.\n
Evidence: references/quick-reference.md includes an add ref command which allows cloning of external repositories from user-supplied URLs to manage project references.\n- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection via the processing of external repository content.\n
Ingestion points: The skill pulls content from remote git repositories into the local .ref/ directory via git pull as documented in references/sync-procedure.md.\n
Boundary markers: Absent. There are no instructions to delineate or treat content from synced repositories as untrusted data.\n
Capability inventory: The skill has the ability to execute shell commands (npm, grunt, git) and read local files as shown in references/build-workflow.md and references/summarize-commands.md.\n
Sanitization: Absent. The skill analyzes file changes and generates summaries without sanitizing the input data for potential malicious instructions.

obsidian-ops