parallel-agent-orchestration
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements an orchestration pattern where subtasks and contexts are passed to multiple subagents. This creates a surface for indirect prompt injection where instructions embedded in processed data (such as file content during code reviews or campaign metrics during audits) could influence agent behavior.
- Ingestion points:
TaskDecomposer.decomposeandParallelOrchestrator.executeinSKILL.mdprocess task descriptions and context objects. - Boundary markers: Absent; the provided implementation does not include delimiters or instructions to ignore embedded commands in the subtasks.
- Capability inventory:
ParallelOrchestrator.executeinSKILL.mddispatches work to agents viaagent.executewhich can perform operations like account audits, code reviews, or generic execution based on potentially untrusted input. - Sanitization: No input validation or filtering is implemented before passing data to subagents.
Audit Metadata