fiftyone-voodo-design

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses WebFetch to retrieve https://voodo.dev.fiftyone.ai/voodo-llm-reference.md at runtime, which is public web content authored by an external party and ingested as readable markdown into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to WebFetch at runtime the LLM reference https://voodo.dev.fiftyone.ai/voodo-llm-reference.md and to read and apply that fetched content before generating UI code, so the remote file directly controls prompts/instructions and is required for the skill to run.