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:spawn CLI 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}.md files 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:spawn and interacts with the codebase using Serena MCP.\n
  • Sanitization: Data from sub-agent progress files is processed without explicit validation or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 04:49 AM
Security Audit — agent-trust-hub — oma-coordination