company-research
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly uses web_search_advanced_exa (and a browser fallback) to fetch and ingest open-web content—company homepages, news articles, tweets, and public LinkedIn profiles—so the agent will read untrusted, user-generated third‑party content that could carry indirect prompt injection.
Audit Metadata