llamacloud-index

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly calls the runtime API at https://api.cloud.llamaindex.ai/api/v1 (LLAMA_BASE) — and references the MCP endpoint https://mcp.llamaindex.ai/mcp — to fetch arbitrary documents/passages that are injected into the model context and used to generate/ground responses, so remote content can directly control the agent's prompts.