how-a-personal-ai-agent-will-change-your-entire-life-in-1-da

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly states the agent reads and acts on public, user-generated sources—e.g., "daily support reports from X mentions", accessing TikTok, and searching/reading/installing third‑party skills from LarryBrain/ClawHub—so the agent ingests untrusted third‑party content that can influence its decisions and tool use.