oma-coordination

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the oh-my-ag CLI tool to manage sub-agents.
  • Example command: oh-my-ag agent:spawn backend "task description" session-id -w ./backend &.
  • Instructions include the use of background processes (&) and the wait command for parallel task coordination.
  • The skill references a local script path: .agents/skills/orchestrator/scripts/spawn-agent.sh.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) by interpolating untrusted user requirements into CLI command arguments.
  • Ingestion points: User-provided task descriptions are passed directly as string arguments to the oh-my-ag command in SKILL.md and resources/examples.md.
  • Boundary markers: None identified; the instructions do not specify delimiters or safety wrappers for the interpolated strings.
  • Capability inventory: The agent has the capability to execute shell commands and manage background processes.
  • Sanitization: No explicit sanitization or input validation is described within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 09:35 PM