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's consult flow (scripts/consult_llm.py and SKILL.md, with endpoints listed in references/providers.md) sends prompts to external LLM providers (Gemini/OpenAI/Qwen) and ingests their responses, which the workflow explicitly requires the agent to read, summarize, reconcile, and potentially act on—exposing it to untrusted third-party content that could contain indirect prompt injections.