content-atomizer

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md's "Deep Mode" explicitly instructs the agent to "Use WebSearch to find top-performing content in their niche" and then "customize hooks" and algorithm/practice recommendations based on those findings, meaning the agent will fetch and interpret open/public third-party content that can materially change its outputs.