orchestrator-mgmt
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to manage and execute scripts and background processes via the 'command' and 'args' configuration fields. This capability allows the agent to start, stop, and restart arbitrary executables as part of its primary orchestrator functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from two main sources: dynamic configuration (adding/updating scripts) and log viewing (reading stdout/stderr from managed processes). There are no specific boundary markers or sanitization procedures mentioned for these ingestion points, creating a potential surface for indirect prompt injection if the logs or script metadata contain instructions targeted at the agent.
Audit Metadata