comprehensive-enrichment

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly ingests untrusted public third-party content (e.g., LinkedIn profile/posts via fiber /v1/linkedin-live-fetch/profile-posts, Twitter/X via nyne /person/newsfeed, website scraping via scrapegraph /v1/smartscraper, and open web searches via linkup /search) and requires the agent to read and act on that content as part of its enrichment workflow, so external instructions could materially influence decisions and follow-up actions.