The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]:\n
Ingestion points: The skill reads from user-controlled files including AGENTS.md, the Outline file, and various MEMORY.md files located within .omx/omxr/agent-memory/.\n
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for content read from external source documents.\n
Capability inventory: The skill has the capability to read and write local files and execute shell commands such as mkdir.\n
Sanitization: There is no evidence of sanitization, validation, or filtering of the content ingested from external files before it is interpolated into memories or reports.\n- [COMMAND_EXECUTION]: The workflow explicitly instructs the agent to execute shell commands like mkdir -p for directory management and references local Python scripts for figure processing within the $CODEX_PLUGIN_ROOT environment.

sync