meta-router

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill classifies user intent to route tasks to specific sub-skills, creating a surface for indirect prompt injection.\n
  • Ingestion points: User input is parsed for trigger keywords in SKILL.md.\n
  • Boundary markers: No boundary delimiters or instructions to disregard nested instructions are provided.\n
  • Capability inventory: The skill routes to high-privilege skillsets including tools-router (shell/database access) and build-router (code deployment).\n
  • Sanitization: No sanitization or input validation logic is defined to prevent malicious payloads from influencing routing decisions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:30 PM