multi-llm-consult

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill runs a consult script that queries external LLM providers (e.g., consult_llm.py --provider gemini|codex|qwen) and ingests their responses for comparison, so the agent will read untrusted third‑party model output that could contain indirect prompt injections.