deep-reading-analyst

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

• Third-party content exposure detected (high risk: 0.90). The skill's Level 4 Research workflow explicitly instructs the agent to "Use web_search to find 2-3 related sources" and is triggered when users provide URLs/long-form content, meaning the agent will fetch and read open/public third-party webpages as part of its analysis (SKILL.md, Level 4 Research and trigger conditions).