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 the Agent tool call within SKILL.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 Agent tool 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
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:49 PM
Security Audit — agent-trust-hub — specialist-data-agents-orchestrator