social-media-scrape

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches public, user-generated social media content from the Scrape Creators API endpoints (e.g., GET https://api.scrapecreators.com/v1/tiktok/search/keyword and /v1/instagram/user/reels) as shown in SKILL.md and the scripts, and the agent parses and acts on captions, metadata, and media URLs (sorting, summarizing, choosing download URLs), so untrusted third-party content can materially influence tool behavior.