specialist-data-agents-orchestrator
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates external user input into the initialization prompt for a specialized sub-agent.\n
- Ingestion points: The variable
{the user's question}in theAgenttool call withinSKILL.md.\n - Boundary markers: None. The user input is directly concatenated into the sub-agent's prompt without delimiters or protective instructions that would distinguish it from the system instructions.\n
- Capability inventory: The skill uses the
Agenttool to coordinate a pipeline of specialist agents including Product Manager, UX Architect, Developer, QA, and Integration agents via a specialized orchestrator agent.\n - Sanitization: None. The skill does not perform any escaping, validation, or filtering of the user-supplied content before it is processed by the sub-agent.
Audit Metadata