instagram-pipeline

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-generated Instagram content (captions, media URLs, collection names) from Instagram's public endpoints (e.g., scripts/socmed/platforms/instagram/api_bootstrap.py calling https://www.instagram.com/api/v1/feed/saved/posts/ and browser_enricher.py calling the GraphQL endpoint), and then processes that content (filters by collection, downloads media, runs Whisper/OCR in scripts/socmed/platforms/instagram/media_extractor.py) so third-party content directly influences pipeline actions and outputs.