oma-coordination
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
oma agent:spawnCLI command to initiate sub-agents for specialized tasks like PM, backend development, and QA. This is the intended mechanism for the coordination workflow.\n- [PROMPT_INJECTION]: A surface for indirect prompt injection exists because the skill instructs the agent to monitor progress files created by other sub-agents.\n - Ingestion points: Reads
progress-{agent}.mdfiles generated by sub-agents to monitor status.\n - Boundary markers: Absent; instructions do not provide delimiters for separating internal logic from external sub-agent data.\n
- Capability inventory: Executes sub-processes via
oma agent:spawnand interacts with the codebase using Serena MCP.\n - Sanitization: Data from sub-agent progress files is processed without explicit validation or filtering.
Audit Metadata