The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute maintenance operations using the gbrain CLI, such as gbrain extract links, gbrain autopilot --install, and gbrain apply-migrations. These commands are standard administrative tasks for the tool's ecosystem.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes user-controlled markdown files from the ~/brain directory.
Ingestion points: Markdown content is read from the local ~/brain directory via get_page and gbrain extract commands.
Boundary markers: No specific delimiters are used to protect the agent from instructions embedded within the processed markdown files.
Capability inventory: The skill possesses file-writing capabilities (put_page, add_link) and the ability to execute shell commands via the gbrain CLI.
Sanitization: There is no evidence of sanitization or validation performed on the ingested markdown content.

maintain