awesome-openclaw-usecases-zh

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflows explicitly ingest and act on untrusted, user-generated third‑party content — e.g., fetching meeting recordings from open.feishu.cn and transcribing them in meeting-notes-action-items.md, scraping/publishing Xiaohongshu posts in cn-xiaohongshu-automation.md, and using web-search/github_trending/perplexity_search in the multi-agent examples — and then use that content to drive agent decisions and tool actions.