oma-coordination

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: Analysis of the skill instructions and examples reveals no malicious patterns, prompt injections, or unauthorized data access.
  • [COMMAND_EXECUTION]: The skill utilizes the 'oma agent spawn' CLI command to orchestrate specialist agents. This is an intended functional capability for multi-agent project management and uses standard shell execution patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for ingesting external data from user prompts and sub-agent progress files to guide coordination.
  • Ingestion points: Project context and agent progress artifacts.
  • Boundary markers: Manual verification steps and contract alignment checks.
  • Capability inventory: Sub-agent spawning and workspace management.
  • Sanitization: Verification and monitoring instructions for the supervising agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 04:52 PM