daily-ai-agent-aigc-top-news-dingtalk

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md and cron prompt) explicitly instructs fetching and scraping open/public third-party sources such as Hacker News, GitHub (releases/PRs/Trending), Hugging Face, official product web pages and media/search results, which the agent must read and use to decide what to publish—exposing it to untrusted/user-generated content that could carry indirect prompt-injection instructions.