The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill uses local vault files to provide context for coaching sessions, which introduces a surface for indirect instructions to influence agent behavior.\n
Ingestion points: The agent reads data from personal.habits_path, personal.okr_file, and project files defined in personal.project_refs and signal.project_refs.\n
Boundary markers: There are no instructions for using delimiters or boundary markers to isolate these data sources from the agent's primary instructions.\n
Capability inventory: The skill has access to Read, Write, Glob, Grep, and Bash tools, allowing for broad file system interaction based on the interpreted data.\n
Sanitization: The protocol does not include steps to sanitize or validate the content of the external files before processing.

coach