social-media-scraping-scrapecreators

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow calls a scraping API (e.g., /v1/twitter/tweet, /v1/linkedin/post, /v1/instagram/post, /v1/tiktok/search/hashtag) using user-supplied URLs/handles, and the scraped profile/post text from those third-party platforms is outsider-authored free text that can be ingested into the agent’s LLM context.