research-router-skill

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFE
Full Analysis
  • Orchestration Logic: The skill defines how to route broad research questions to specific specialized modules. This is a functional design that does not introduce security vulnerabilities.
  • Subagent Parallelization: The skill utilizes subagents for parallel evidence gathering. These subagents are given bounded, read-only objectives, which is a safe practice for complex retrieval tasks.
  • Absence of Malicious Vectors: A comprehensive scan for prompt injection, credentials exposure, and remote code execution revealed no security findings. The skill instructions align with its stated purpose of improving research synthesis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 12:20 PM
Security Audit — agent-trust-hub — research-router-skill