bevy

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md "First moves" explicitly directs the agent to check public Bevy resources (e.g., https://bevyengine.org/examples/ and https://bevyengine.org/learn/migration-guides/), which are open/public third‑party web pages the agent is expected to read and whose API/instructions can materially affect code and tool decisions.