industry-research

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and Web Intelligence/workflows sections explicitly call recoup research web/report/extract and endpoints like instagram-posts to scrape and ingest public web pages and social media posts (e.g., "recoup research web 'query'" and "recoup research extract 'https://...'") which the agent is instructed to read, synthesize, and act on for pitching, touring, and other decisions, so untrusted third-party content can materially influence actions.