The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the oma CLI and local shell scripts like spawn-agent.sh to coordinate tasks across different agents. This is an essential part of the manual coordination workflow described.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection where untrusted user requirements are passed as arguments to shell commands. Ingestion points: User-provided task descriptions and project requirements enter the workflow as described in SKILL.md and resources/examples.md. Boundary markers: None are present; user input is directly interpolated into command strings like oma agent:spawn. Capability inventory: The workflow relies on subprocess execution capabilities to run CLI tools. Sanitization: The skill instructions do not include any steps for validating or sanitizing the strings provided by the user before they are used in the command line.

oma-coordination