The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses an unsafe interpolation pattern where user-supplied arguments are placed directly after a 'Task:' label at the end of the instructions. This can lead to the agent interpreting user input as direct commands to override behavior.
[COMMAND_EXECUTION]: The skill facilitates the execution of secondary setup and diagnostic tools (omc-setup, omc-doctor, mcp-setup). While the specific commands are not in this file, setup utilities traditionally require high-privilege shell access and file system modifications.
[PROMPT_INJECTION]: Indirect Prompt Injection Surface:
Ingestion points: User-provided input is captured via {{ARGUMENTS}}, {{ARGUMENTS_AFTER_DOCTOR}}, and {{ARGUMENTS_AFTER_MCP}} in SKILL.md.
Boundary markers: Absent. The arguments are interpolated directly into the prompt text without XML tags, triple quotes, or other delimiters to isolate untrusted content.
Capability inventory: The skill routes to omc-setup, omc-doctor, and mcp-setup (referenced in SKILL.md), which are intended for system configuration and diagnostics.
Sanitization: Absent. There are no instructions for the agent to validate, escape, or ignore embedded instructions within the user-provided arguments.

setup