contact-finder-contactout

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow accepts user-supplied LinkedIn profile URLs/emails/domains and calls external enrichment endpoints (e.g., /v1/linkedin/enrich and /v1/people/linkedin), which can cause the agent/LLM context to ingest free-form text scraped from those outsider-authored web pages (LinkedIn profiles) or other third-party sources.