Swarm Orchestration
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
npx agentic-flowto execute various lifecycle hooks includingswarm-init,agent-spawn, andtask-orchestrate. These commands facilitate swarm setup and management. - [EXTERNAL_DOWNLOADS]: The skill relies on the
agentic-flowpackage, which is the core dependency for the described functionality and is fetched from the npm registry. - [PROMPT_INJECTION]: The skill implements an interface for task orchestration that processes natural language input.
- Ingestion points: The
--taskargument intask-orchestrateand thegoalfield in theautoOrchestratefunction inSKILL.md. - Boundary markers: No delimiters or instructions to ignore embedded commands are present in the examples.
- Capability inventory: The skill orchestrates multiple agents (coder, tester, reviewer) and executes parallel or sequential task pipelines.
- Sanitization: No explicit sanitization or validation of the input goals or tasks is documented.
Audit Metadata